WO2023024501A1 - 音频数据处理方法、装置、设备以及存储介质 - Google Patents

音频数据处理方法、装置、设备以及存储介质 Download PDF

Info

Publication number
WO2023024501A1
WO2023024501A1 PCT/CN2022/082305 CN2022082305W WO2023024501A1 WO 2023024501 A1 WO2023024501 A1 WO 2023024501A1 CN 2022082305 W CN2022082305 W CN 2022082305W WO 2023024501 A1 WO2023024501 A1 WO 2023024501A1
Authority
WO
WIPO (PCT)
Prior art keywords
fundamental frequency
audio
audio data
data
human voice
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2022/082305
Other languages
English (en)
French (fr)
Inventor
王艺鹏
刘云峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to US17/915,624 priority Critical patent/US20240212703A1/en
Priority to JP2022560146A priority patent/JP7465992B2/ja
Priority to EP22773390.4A priority patent/EP4167226B1/en
Publication of WO2023024501A1 publication Critical patent/WO2023024501A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/003—Changing voice quality, e.g. pitch or formants
    • G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
    • G10L21/013—Adapting to target pitch
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H1/00—Details of electrophonic musical instruments
    • G10H1/02—Means for controlling the tone frequencies, e.g. attack or decay; Means for producing special musical effects, e.g. vibratos or glissandos
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0272—Voice signal separating
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H1/00—Details of electrophonic musical instruments
    • G10H1/36—Accompaniment arrangements
    • G10H1/361—Recording/reproducing of accompaniment for use with an external source, e.g. karaoke systems
    • G10H1/366—Recording/reproducing of accompaniment for use with an external source, e.g. karaoke systems with means for modifying or correcting the external signal, e.g. pitch correction, reverberation, changing a singer's voice
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G10L13/04—Details of speech synthesis systems, e.g. synthesiser structure or memory management
    • G10L13/047—Architecture of speech synthesisers
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
    • G10L19/032—Quantisation or dequantisation of spectral components
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • G10L21/0232—Processing in the frequency domain
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0272—Voice signal separating
    • G10L21/0308—Voice signal separating characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/09—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being zero crossing rates
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/93—Discriminating between voiced and unvoiced parts of speech signals
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/005—Musical accompaniment, i.e. complete instrumental rhythm synthesis added to a performed melody, e.g. as output by drum machines
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/021—Background music, e.g. for video sequences or elevator music
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/041—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal based on mfcc [mel -frequency spectral coefficients]
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/155—Musical effects
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/325—Musical pitch modification
    • G10H2210/331—Note pitch correction, i.e. modifying a note pitch or replacing it by the closest one in a given scale
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
    • G10H2250/311—Neural networks for electrophonic musical instruments or musical processing, e.g. for musical recognition or control, automatic composition or improvisation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
    • G10H2250/315—Sound category-dependent sound synthesis processes [Gensound] for musical use; Sound category-specific synthesis-controlling parameters or control means therefor
    • G10H2250/455—Gensound singing voices, i.e. generation of human voices for musical applications, vocal singing sounds or intelligible words at a desired pitch or with desired vocal effects, e.g. by phoneme synthesis
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the present disclosure relates to the technical field of audio processing, in particular to the technical field of speech synthesis.
  • the electronic sound effect can be used to adjust and beautify the sound, and it is widely used in scenes such as karaoke works or short video works.
  • High-quality electronic sound effects can improve the sound quality of the work.
  • product competitiveness can be enhanced
  • product gameplay can be enriched
  • user interest can be increased.
  • the disclosure provides an audio data processing method, device, equipment, storage medium and program product.
  • an audio data processing method including: decomposing the original audio data to obtain human voice audio data and background audio data; performing electronic processing on the human voice audio data to obtain electronic human voice data sound data; and synthesizing the electronic vocal data and the background audio data to obtain target audio data.
  • an audio data processing device including: a decomposing module for decomposing the original audio data to obtain human voice audio data and background audio data; an electronic sound processing module for processing the human voice The audio data is electronically processed to obtain electronic human voice data; and a synthesis module is used to synthesize the electronic human voice data and the background audio data to obtain target audio data.
  • Another aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores information executable by the at least one processor. instructions, the instructions are executed by the at least one processor, so that the at least one processor can execute the method shown in the embodiments of the present disclosure.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the method shown in the embodiments of the present disclosure.
  • a computer program product including computer programs/instructions, which is characterized in that, when the computer program/instructions are executed by a processor, the steps of the methods shown in the embodiments of the present disclosure are implemented.
  • Fig. 1 schematically shows a flow chart of an audio data processing method according to an embodiment of the present disclosure
  • Fig. 2 schematically shows a flow chart of a method for decomposing raw audio data according to an embodiment of the present disclosure
  • Fig. 3 schematically shows a flow chart of a method for performing electroacoustic processing on human voice audio data according to an embodiment of the present disclosure
  • Fig. 4 schematically shows a flowchart of an audio data processing method according to another embodiment of the present disclosure
  • Fig. 5 schematically shows a block diagram of an audio data processing device according to an embodiment of the present disclosure.
  • Fig. 6 schematically shows a block diagram of an example electronic device that may be used to implement embodiments of the present disclosure.
  • the audio data processing method of the embodiment of the present disclosure will be described below with reference to FIG. 1 . It should be noted that in the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of audio data and other data involved are all in compliance with relevant laws and regulations, and do not violate public order and good customs.
  • FIG. 1 is a flowchart of an audio data processing method according to an embodiment of the present disclosure.
  • the audio data processing method 100 includes decomposing the original audio data to obtain vocal audio data and background audio data in operation S110.
  • the human voice audio data is electronically processed to obtain electronic human voice data.
  • the electronic vocal data and background audio data are synthesized to obtain target audio data.
  • the original audio data may include, for example, human voice information and background sound information, wherein the human voice may be, for example, a singing voice, and the background sound may, for example, be accompaniment music.
  • a sound source separation algorithm can be used to separate the vocal information and background information in the original audio data to obtain vocal audio data containing vocal information and background audio data containing background sound information.
  • the disclosed embodiment by separating the human voice information in the original audio data from the background sound information, converting the human voice information into electronic sound, and then synthesizing the electronically sound human voice information with the background sound information, the Electronization of audio data with both background sound information and human voice information.
  • a neural network may be used to implement a sound source separation algorithm to decompose original audio data.
  • the input of the neural network may be audio data with background sound information and human voice information
  • the output of the neural network may be human voice audio data including human voice information and background audio data including background sound information.
  • the music file and the human voice file can be obtained in advance, and the music file and the human voice file can be cut into segments of equal length to obtain multiple music segments X and multiple vocal segments Y.
  • Each music segment X can be synthesized with a corresponding human voice segment Y to obtain an original audio data Z.
  • Each original audio data Z is used as the input of the neural network, and the music segment X and the human voice segment Y corresponding to the original audio data Z are used as the expected output to train the neural network.
  • music clip X, vocal clip Y and original audio data Z can be preprocessed into Mel spectrum.
  • the output result of the neural network is also based on the Mel spectrum.
  • the output result in the form of the mel spectrum can be synthesized into corresponding original audio data through an algorithm such as the Griffin-Lim (Griffin-Lin) algorithm.
  • Fig. 2 schematically shows a flowchart of a method for decomposing original audio data according to an embodiment of the present disclosure.
  • the method 210 for decomposing original audio data includes determining original mel spectrum data corresponding to the original audio data in operation S211.
  • background mel spectrum data and vocal mel spectrum data corresponding to the original mel spectrum data are determined using a neural network.
  • the background mel spectrum data may include background sound information in the original mel spectrum data
  • the vocal mel spectrum data may include vocal information in the original mel spectrum data
  • background audio data is generated based on the background mel spectrum data
  • vocal audio data is generated based on the vocal mel spectrum data
  • the background audio data can be generated according to the background mel spectrum data through an algorithm such as the Griffin-Lim algorithm, and the vocal audio data can be generated according to the vocal mel spectrum data.
  • the electroacoustic processing of human voice audio data can be realized by quantizing the fundamental frequency of the human voice data.
  • the fundamental frequency, spectral envelope and aperiodic parameters of vocal data can be determined.
  • the fundamental frequency represents the vibration frequency of the vocal cords during pronunciation, which is reflected in the audio frequency as the pitch.
  • the fundamental frequency can be quantized, and the human voice data can be re-synthesized according to the quantized fundamental frequency, spectrum envelope and aperiodic parameters, so as to realize the electroacoustic processing of the human voice audio data.
  • the resynthesized human voice data is electronic vocal data, which includes human voice information with electronic sound effects.
  • Fig. 3 schematically shows a flowchart of a method for electronically processing human voice audio data according to an embodiment of the present disclosure.
  • the method 320 for electronically processing human voice audio data may include, in operation S321 , extracting the original fundamental frequency of the human voice audio data.
  • the original fundamental frequency can be extracted from human voice audio data according to algorithms such as DIO and Harvest.
  • the original fundamental frequency is corrected to obtain the first fundamental frequency.
  • human voice audio data may be divided into multiple audio segments. Then, for each audio segment of the plurality of audio segments, the energy and zero-crossing rate of the audio segment are determined. Based on energy and zero-crossing rate, determine whether an audio segment is a voiced audio segment. Then, a linear interpolation algorithm is used to modify the fundamental frequency of the voiced audio segment.
  • the vocal audio data can be divided into multiple audio segments with a preset unit length, and the length of each audio segment is a preset unit length.
  • the preset unit length can be set according to actual needs.
  • the preset unit length may be any value from 10ms to 40ms.
  • each audio segment is provided with a plurality of sampling points.
  • the energy of an audio clip can be determined based on the value of each sample point in the audio clip. For example, the energy of an audio clip can be calculated according to the following formula:
  • x i represents the value of the i-th sampling point
  • n is the number of sampling points.
  • the number n of sampling points may be determined according to the length and sampling rate of the audio segment. Taking the preset unit length of 10ms as an example, the number n of sampling points can be calculated according to the following formula:
  • sr represents the sampling rate of the audio.
  • the zero-crossing rate of an audio clip can be calculated according to the following formula:
  • ZCR is the zero-crossing rate of the audio clip
  • n is the number of sampling points in the audio clip
  • x i represents the value of the i-th sampling point in the audio clip
  • x i-1 represents the i-1th sampling point in the audio clip value.
  • the number n of sampling points may be determined according to the length and sampling rate of the audio segment. Taking the preset unit length of 10ms as an example, the number n of sampling points can be calculated according to the following formula:
  • sr represents the sampling rate of the audio.
  • the fundamental frequency can be corrected by using the above characteristics.
  • the audio segment For each audio segment, if the energy E of the audio segment is less than the threshold e_min, and the zero-crossing rate ZCR of the audio segment is greater than the threshold zcr_max, then the audio segment is an unvoiced audio segment, and its fundamental frequency is 0. Otherwise, the audio segment is a voiced audio segment with a non-zero fundamental frequency.
  • e_min and zcr_max can be set according to actual needs.
  • the base frequency of the audio segment may be set to 0.
  • the fundamental frequency of each voiced sound audio segment can be extracted according to algorithms such as DIO and Harvest, and then whether the fundamental frequency value of each voiced sound audio segment is 0 is detected one by one.
  • linear interpolation can be performed based on the values of voiced sound audio fragments near the voiced sound audio clip based on a linear interpolation algorithm to obtain a fundamental frequency value that is not 0 as the fundamental frequency of the voiced sound audio clip value.
  • the fundamental frequency values are: 100, 100, 0, 0, 160, and 100. That is, the fundamental frequency values of the 3rd and 4th voiced audio clips are 0. Therefore, linear interpolation can be performed based on non-zero fundamental frequency values near the fundamental frequency values of the third and fourth voiced sound audio clips, that is, linear interpolation can be performed based on the second fundamental frequency value of 100 and the fifth fundamental frequency value of 160,
  • the fundamental frequency values of the 3rd and 4th voiced sound audio clips are obtained as 120 and 140. That is, the corrected six fundamental frequency values are 100, 100, 120, 140, 160, and 100.
  • the first fundamental frequency is adjusted according to predetermined electronic sound parameters to obtain a second fundamental frequency.
  • the predetermined electronic sound parameter may include, for example, an electronic sound degree parameter and/or an electronic sound pitch parameter.
  • the electronic sound degree parameter can be used to control the degree of the electronic sound.
  • the Electronic Tone parameter can be used to control the tone.
  • the electronic sound level parameter may include, for example, 1, 1.2, and 1.4, and the greater the electronic sound level parameter, the more obvious the electronic sound effect.
  • the electronic tone parameters may include -3, -2, -1, +1, +2, +3, for example. Among them, -1, -2, and -3 represent 1, 2, and 3 tones lowered, respectively, and +1, +2, and +3 represent 1, 2, and 3 tones raised, respectively.
  • parameters cannot be adjusted for the electronic sound effect, and the effect is single.
  • two parameters, the degree parameter of the electronic sound and the pitch parameter of the electronic sound are set to control the effect of the electronic sound, which can meet different user demands.
  • the variance of the fundamental frequency and/or the average value of the fundamental frequency may be determined according to the fundamental frequencies of all voiced audio segments. Determine the modified fundamental frequency variance according to the electronic sound level parameter and the fundamental frequency variance, and/or determine the corrected fundamental frequency average value according to the electronic sound level parameter and the fundamental frequency average value. Then, according to the modified fundamental frequency variance and/or the corrected fundamental frequency average value, the first fundamental frequency is adjusted to obtain the second fundamental frequency.
  • the variance of the fundamental frequencies of all voiced sound audio segments may be calculated as the fundamental frequency variance, and the average value of the fundamental frequencies of all the voiced sound audio segments may be calculated as the average fundamental frequency.
  • the modified fundamental frequency variance can be calculated according to the following formula:
  • new_var is the variance of the modified fundamental frequency
  • var is the variance of the fundamental frequency
  • a is the parameter of the electronic sound level.
  • the corrected fundamental frequency average can be calculated according to the following formula:
  • new_mean is the average value of the modified fundamental frequency
  • mean is the average value of the fundamental frequency
  • b is the electronic tone parameter.
  • the second fundamental frequency can be calculated according to the following formula:
  • F0' is the second fundamental frequency.
  • each key frequency of the piano can be used as the target frequency to quantize the fundamental frequency of the vocal data.
  • the frequency range can be determined according to the following formula:
  • scale is the frequency range
  • F0' is the second fundamental frequency
  • the third fundamental frequency can be determined according to the following formula:
  • F0" is the third fundamental frequency.
  • the spectral envelope and the aperiodic parameters can be determined according to the human voice audio data and the first fundamental frequency. Then the electronic vocal data can be determined according to the third fundamental frequency, spectrum envelope and aperiodic parameters.
  • Fig. 4 schematically shows a flowchart of an audio data processing method according to another embodiment of the present disclosure.
  • the audio data processing method 400 includes, in operation S401 , determining whether the audio data (referred to as audio) contains accompaniment music (referred to as accompaniment). If the accompaniment is included, perform operation S402. If only human voice is included but no accompaniment is included, perform operation S403.
  • operation S402 the human voice is separated from the accompaniment by using a sound source separation algorithm. Then perform operation S403 for the separated human voice.
  • the fundamental frequency is corrected based on the zero-crossing rate and the energy to obtain F0.
  • the spectrum envelope SP and the aperiodic parameter AP are calculated using the human voice and the corrected fundamental frequency F0.
  • the fundamental frequency is adjusted and F0' is obtained according to the electronic sound level parameter a and the electronic sound pitch parameter b set by the user.
  • operation S409 if the audio has an accompaniment, operation S410 is performed. Otherwise, perform operation S411.
  • the accompaniment is also mixed into the human voice to generate the final audio with electronic sound effect.
  • Fig. 5 schematically shows a block diagram of an audio data processing device according to an embodiment of the present disclosure.
  • the audio data processing device 500 includes a decomposition module 510 , an electronic sound processing module 520 and a synthesis module 530 .
  • Decomposition module 510 configured to decompose the original audio data to obtain vocal audio data and background audio data.
  • the electronic sound processing module 520 is configured to perform electronic sound processing on the human voice audio data to obtain electronic sound human voice data.
  • the synthesis module 530 is used for synthesizing the electronic vocal data and the background audio data to obtain the target audio data.
  • the decomposition module may include a mel spectrum determination submodule, a decomposition submodule and a generation submodule.
  • the mel spectrum determination submodule can be used to determine the original mel spectrum data corresponding to the original audio data.
  • the decomposition sub-module can be used to determine background mel spectrum data and vocal mel spectrum data corresponding to the original mel spectrum data by using a neural network.
  • the generation sub-module can be used to generate background audio data according to the background Mel spectrum data, and generate human voice audio data according to the vocal Mel spectrum data.
  • the electronic sound processing module may include an extraction sub-module, a correction sub-module, an adjustment sub-module, a quantization sub-module and an electronic sound determination sub-module.
  • the extraction sub-module can be used to extract the original fundamental frequency of the human voice audio data.
  • the correction sub-module can be used to correct the original fundamental frequency to obtain the first fundamental frequency.
  • the adjustment sub-module can be used to adjust the first fundamental frequency according to predetermined electronic sound parameters to obtain the second fundamental frequency.
  • the quantization sub-module can be used to perform quantization processing on the second fundamental frequency to obtain the third fundamental frequency.
  • the electronic sound determination sub-module can be used to determine electronic sound human voice data according to the third fundamental frequency.
  • the correction submodule may include: a segmentation unit, an energy determination unit, a zero-crossing rate determination unit, a voiced sound determination unit, and a correction unit.
  • the segmentation unit can be used to divide the human voice audio data into multiple audio segments.
  • the energy determination unit may be configured to determine the energy of the audio segment for each audio segment in the plurality of audio segments.
  • the zero-crossing rate determination unit can be used for determining the zero-crossing rate of the audio segment for each audio segment in the plurality of audio segments.
  • the voiced sound judging unit can be used to determine whether the type of the audio segment is a voiced sound audio segment according to the energy and the zero-crossing rate.
  • the correction unit can be used to correct the fundamental frequency of the voiced sound audio segment by using a linear interpolation algorithm.
  • an audio segment is provided with a plurality of sampling points.
  • the energy determination unit can also be used to determine the energy of the audio segment according to the value of each sampling point in the audio segment.
  • the zero-crossing rate determination unit can also be used to determine whether the values of every two adjacent sampling points in the audio segment have opposite signs to each other, and then determine that the number of times that adjacent sampling points in the audio segment are of different signs accounts for all The ratio of the number of sampling points is used as the zero-crossing rate.
  • the predetermined electronic sound parameters may include electronic sound degree parameters and/or electronic sound tone parameters.
  • the adjustment submodule may include a first determination unit, a second determination unit and an adjustment unit.
  • the first determination unit may be configured to determine the variance of the fundamental frequency and/or the average value of the fundamental frequency according to the fundamental frequency of the voiced audio segment.
  • the second determination unit may be configured to determine the modified fundamental frequency variance according to the electronic sound degree parameter and the fundamental frequency variance, and/or determine the modified fundamental frequency average value according to the electronic sound degree parameter and the fundamental frequency average value.
  • the adjusting unit may be configured to adjust the first fundamental frequency according to the modified fundamental frequency variance and/or the corrected fundamental frequency average value to obtain the second fundamental frequency.
  • the quantization submodule may include a frequency range determination unit and a third fundamental frequency determination unit.
  • the frequency range determination unit can be used to determine the frequency range according to the following formula:
  • scale is a frequency range
  • F0' is the second fundamental frequency
  • the third fundamental frequency determination unit can be used to determine the third fundamental frequency based on the frequency range according to the following formula:
  • F0" is the third fundamental frequency.
  • the above-mentioned audio data processing apparatus may further include a determination module, which may be configured to determine a spectrum envelope and aperiodic parameters according to the vocal audio data and the first fundamental frequency.
  • the electronic sound determining submodule may also be used to determine electronic sound human voice data according to the third fundamental frequency, spectrum envelope and aperiodic parameters.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 6 schematically shows a block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 600 includes a computing unit 601 that can execute according to a computer program stored in a read-only memory (ROM) 602 or loaded from a storage unit 608 into a random-access memory (RAM) 603. Various appropriate actions and treatments. In the RAM 603, various programs and data necessary for the operation of the device 600 can also be stored.
  • the computing unit 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604 .
  • the I/O interface 605 includes: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc. ; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 609 allows the device 600 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • the computing unit 601 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 601 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the computing unit 601 executes various methods and processes described above, such as audio data processing methods.
  • the audio data processing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608 .
  • part or all of the computer program may be loaded and/or installed on the device 600 via the ROM 602 and/or the communication unit 609.
  • the computer program When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the audio data processing method described above may be performed.
  • the computing unit 601 may be configured to execute the audio data processing method in any other suitable way (for example, by means of firmware).
  • Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system of systems
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.
  • steps may be reordered, added or deleted using the various forms of flow shown above.
  • each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Circuit For Audible Band Transducer (AREA)

Abstract

一种音频数据处理方法（100），涉及语音合成技术领域，包括：分解原始音频数据，得到人声音频数据和背景音频数据（S110）；对人声音频数据进行电音化处理，得到电音人声数据（S120）；以及将电音人声数据和背景音频数据合成，得到目标音频数据（S130）。还涉及一种音频数据处理装置（500）、电子设备（600）以及存储介质（608）。

Description

音频数据处理方法、装置、设备以及存储介质
本申请要求于2021年8月24日提交的、申请号为202110978065.3的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及音频处理技术领域，尤其涉及语音合成技术领域。
背景技术
电音效果作为一种声音滤镜，可以用于调整美化声音，在K歌作品或小视频作品等场景中有广泛的应用。优质的电音效果能提升作品的声音质量。对于应用程序产品来说，若能提供优质的电音效果，则可以提升产品竞争力，丰富产品玩法，增加用户趣味。
发明内容
本公开提供了一种音频数据处理方法、装置、设备、存储介质以及程序产品。
根据本公开的一方面，提供了一种音频数据处理方法，包括：分解原始音频数据，得到人声音频数据和背景音频数据；对所述人声音频数据进行电音化处理，得到电音人声数据；以及将所述电音人声数据和所述背景音频数据合成，得到目标音频数据。
根据本公开的另一方面，提供了一种音频数据处理装置，包括：分解模块，用于分解原始音频数据，得到人声音频数据和背景音频数据；电音处理模块，用于对所述人声音频数据进行电音化处理，得到电音人声数据；以及合成模块，用于将所述电音人声数据和所述背景音频数据合成，得到目标音频数据。
本公开的另一个方面，提供了一种电子设备，包括：至少一个处理器；以及与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本公开实施例所示的方法。
根据本公开实施例的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行本公开实施例所示的方法。
根据本公开实施例的另一方面，提供了一种计算机程序产品，包括计算机程序/指令， 其特征在于，该计算机程序/指令被处理器执行时实现本公开实施例所示方法的步骤。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
附图用于更好地理解本方案，不构成对本公开的限定。其中：
图1示意性示出了根据本公开实施例的音频数据处理方法的流程图；
图2示意性示出了根据本公开的实施例的分解原始音频数据的方法流程图；
图3示意性示出了根据本公开的实施例的对人声音频数据进行电音化处理的方法流程图；
图4示意性示出了根据本公开另一实施例的音频数据处理方法的流程图；
图5示意性示出了根据本公开实施例的音频数据处理装置的框图；以及
图6示意性示出了可以用来实施本公开的实施例的示例电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
以下将结合图1对本公开实施例的音频数据处理方法进行描述。需要说明的是，本公开的技术方案中，所涉及的音频数据等数据的收集、存储、使用、加工、传输、提供和公开等处理，均符合相关法律法规的规定，且不违背公序良俗。
图1是根据本公开实施例的音频数据处理方法的流程图。
如图1所示，该音频数据处理方法100包括在操作S110，分解原始音频数据，得到人声音频数据和背景音频数据。
在操作S120，对人声音频数据进行电音化处理，得到电音人声数据。
在操作S130，将电音人声数据和背景音频数据合成，得到目标音频数据。
根据本公开的实施例，原始音频数据例如可以包括人声信息和背景声音信息，其中，人声例如可以为歌声，背景声音例如可以为伴奏音乐。在本实施例中，例如可以 利用声源分离算法将原始音频数据中的人声信息和背景信息分离开来，得到包含人声信息的人声音频数据和包含背景声音信息的背景音频数据。
根据公开的实施例，通过将原始音频数据中的人声信息和背景声音信息分离，对人声信息进行电音化，然后将电音化后的人声信息与背景声音信息合成，实现了对同时具有背景声音信息和人声信息的音频数据的电音化。
根据本公开的实施例，可以利用神经网络来实现声源分离算法，以分解原始音频数据。该神经网络的输入可以为带有背景声音信息和人声信息的音频数据，该神经网络的输出可以包含人声信息的人声音频数据和包含背景声音信息的背景音频数据。
根据本公开的实施例，可以预先获取音乐文件与人声文件，将音乐文件与人声文件切成等长片段，得到多个音乐片段X和多个人声片段Y。可以分别将每个音乐片段X和一个对应的人声片段Y合成，得到一个原始音频数据Z。分别以每个原始音频数据Z为神经网络的输入，以原始音频数据Z对应的音乐片段X和人声片段Y为预期输出，对神经网络进行训练。此外，为了提高训练效果，加快网络收敛，音乐片段X、人声片段Y和原始音频数据Z均可预处理为梅尔频谱。相应地，神经网络的输出结果也为基于梅尔频谱。示例性地，该梅尔频谱形式的输出结果可通过Griffin-Lim(格里芬-林)算法等算法合成对应的原始音频数据。
基于此，下面参考图2，结合具体实施例对上文所示的分解原始音频数据的方法做进一步说明。本领域技术人员可以理解，以下示例实施例仅用于理解本公开，本公开并不局限于此。
图2示意性示出了根据本公开的实施例的分解原始音频数据的方法流程图。
如图2所示，该分解原始音频数据的方法210包括在操作S211，确定与原始音频数据对应的原始梅尔频谱数据。
然后，在操作S212，使用神经网络确定与原始梅尔频谱数据对应的背景梅尔频谱数据和人声梅尔频谱数据。
根据本公开的实施例，背景梅尔频谱数据可以包含原始梅尔频谱数据中的背景声音信息，人声梅尔频谱数据可以包含原始梅尔频谱数据中的人声信息。
在操作S213，根据背景梅尔频谱数据，生成背景音频数据，并根据人声梅尔频谱数据，生成人声音频数据。
根据本公开的实施例，可以通过Griffin-Lim算法等算法根据背景梅尔频谱数据，生成背景音频数据，并根据人声梅尔频谱数据，生成人声音频数据。
根据本公开的实施例，可以通过对人声数据的基频进行量化来实现对人声音频数据进行电音化处理。例如，可以确定人声数据的基频、频谱包络和非周期参数。其中，基频表示的是发音时声带的振动频率，体现在音频上即为音调的高低。接下来，可以对基频进行量化，根据量化后的基频、频谱包络和非周期参数，重新合成人声数据，以实现对人声音频数据进行电音化处理。其中，该重新合成的人声数据即电音人声数据，包含带有电音效果的人声信息。
下面参考图3，结合具体实施例对上文所示的对人声音频数据进行电音化处理的方法做进一步说明。本领域技术人员可以理解，以下示例实施例仅用于理解本公开，本公开并不局限于此。
图3示意性示出了根据本公开的实施例的对人声音频数据进行电音化处理的方法流程图。
如图3所示，该对人声音频数据进行电音化处理的方法320可以包括在操作S321，提取人声音频数据的原始基频。
根据本公开的实施例，例如可以根据DIO、Harvest等算法从人声音频数据中提取原始基频。
在操作S322，对原始基频进行修正，得到第一基频。
根据本公开的实施例，通过修正基频，可以提升电音效果。例如，本实施例中，可以将人声音频数据分为多个音频片段。然后针对多个音频片段中的每个音频片段，确定音频片段的能量和过零率。根据能量和过零率，确定音频片段是否为浊音音频片段。接着利用线性插值算法，对浊音音频片段的基频进行修正。
根据本公开的实施例，可以以预设单位长度将人声音频数据分为多个音频片段，每个音频片段的长度为一个预设单位长度。其中，预设单位长度可以根据实际需要进行设置。示例性地，本实施例中，预设单位长度可以为10ms至40ms中任意一个值。
根据本公开的实施例，每个音频片段设置有多个采样点。可以根据音频片段中每个采样点的数值，确定音频片段的能量。例如，可以根据以下公式计算音频片段的能量：
Figure PCTCN2022082305-appb-000001
其中，x i表示第i个采样点的数值，n为采样点的数量。
根据本公开的实施例，采样点的数量n可以根据音频片段的长度和采样率来确定。以预设单位长度为10ms为例，可以根据以下公式计算采样点的数量n：
n＝10/1000*sr＝0.01sr
其中，sr表示音频的采样率。
根据本公开的实施例，可以确定音频片段中每两个相邻采样点的数值是否彼此符号相反。然后确定音频片段中相邻采样点为异号的次数占所有采样点个数的比值，作为过零率。
根据本公开的实施例，可以根据以下公式计算音频片段的过零率：
Figure PCTCN2022082305-appb-000002
其中，ZCR为音频片段的过零率，n为音频片段中采样点的数量，x i表示音频片段中第i个采样点的数值，x i-1表示音频片段中第i-1个采样点的数值。
根据本公开的实施例，采样点的数量n可以根据音频片段的长度和采样率来确定。以预设单位长度为10ms为例，可以根据以下公式计算采样点的数量n：
n＝10/1000*sr＝0.01sr
其中，sr表示音频的采样率。
人体在发音时，对于清音的发声，声带不震动，因此对应的基频为0。而对于浊音的发声，声带振动，对应的基频不为0。基于此，本实施例中，可以利用上述特性来修正基频。
例如，对于每个音频片段，如果该音频片段的能量E小于阈值e_min，且该音频片段的过零率ZCR大于阈值zcr_max，则该音频片段为清音音频片段，其基频为0。否则，该音频片段为浊音音频片段，其基频非0。其中，e_min与zcr_max可根据实际需要进行设置。
对于每个清音音频片段，可以将该音频片段的基频设置为0。对于浊音音频片段， 可以根据DIO、Harvest等算法提取每个浊音音频片段的基频，然后逐一检测每个浊音音频片段的基频值是否为0。对于基频值为0的浊音音频片段，可以基于线性插值算法，利用根据该浊音音频片段附近的浊音音频片段值进行线性插值，得到一个不为0的基频值作为该浊音音频片段的基频值。
例如，浊音音频片段有6个，基频值分别为：100，100，0，0，160，100。即第3个和第4个浊音音频片段的基频值为0。因此可以根据第3个和第4个浊音音频片段的基频值附近非零的基频值进行线性插值，即根据第2个基频值100和第五个基频值160，进行线性插值，得到第3个和第4个浊音音频片段的基频值为120和140。即修正后的6个基频值为100，100，120，140，160，100。
然后，在操作S323，根据预定电音参数，调整第一基频，得到第二基频。
根据本公开的实施例，预定电音参数例如可以包括电音程度参数和/或电音音调参数。其中，电音程度参数可以用于控制电音的程度。电音音调参数可以用于控制音调。示例性地，本实施例中，电音程度参数例如可以包括1、1.2、1.4，电音程度参数越大则电音效果越明显。电音音调参数例如可以包括-3、-2、-1、+1、+2、+3。其中，-1、-2、-3分别表示降1、2、3个调，+1、+2、+3分别表示升1、2、3个调。
相关技术中，电音效果无法调整参数，效果单一。根据本公开的实施例，基于电音的特性，设置了电音程度参数和电音音调参数两个参数，用于控制电音效果，可以满足不同的用户需求。
根据本公开的实施例，可以根据所有浊音音频片段的基频，确定基频方差和/或基频平均值。根据电音程度参数和基频方差，确定修正基频方差，以及/或者，根据电音程度参数和基频平均值，确定修正基频平均值。然后根据修正基频方差和/或修正基频平均值，调整第一基频，得到第二基频。
示例性地，本实施例中，可以计算所有浊音音频片段的基频的方差，作为基频方差，计算所有浊音音频片段的基频的平均值，作为基频平均值。
然后，可以根据以下公式计算修正基频方差：
new_var＝var*a
其中，new_var为修正基频方差，var为基频方差，a为电音程度参数。
可以根据以下公式计算修正基频平均值：
new_mean＝mean*2 b/12
其中，new_mean为修正基频平均值，mean为基频平均值，b为电音音调参数。
接下来，可以根据以下公式计算第二基频：
Figure PCTCN2022082305-appb-000003
其中，F0′为第二基频。
在操作S324，针对第二基频进行量化处理，得到第三基频。
自然的音频中，声音音调是抑扬顿挫的，是逐渐变化的，而电音则是将音调量化到特定的音阶上，使得音调不连续变化，类似于电子乐器发出的音调。基于此，根据本公开的实施例，可以以钢琴的每个按键频率为目标频率来对人声数据的基频进行量化。
示例性地，本实施例中，可以根据以下公式确定频率范围：
Figure PCTCN2022082305-appb-000004
其中，scale为频率范围，F0′为第二基频；
然后，可以基于频率范围，根据以下公式确定第三基频：
Figure PCTCN2022082305-appb-000005
其中，F0″为第三基频。
在操作S325，根据第三基频，确定电音人声数据。
根据本公开的实施例，可以根据人声音频数据和第一基频，确定频谱包络和非周期参数。然后可以根据第三基频、频谱包络和非周期参数，确定电音人声数据。
下面参考图4，结合具体实施例对上文所示的音频数据处理方法做进一步说明。本领域技术人员可以理解，以下示例实施例仅用于理解本公开，本公开并不局限于此。
图4示意性示出了根据本公开另一实施例的音频数据处理方法的流程图。
如图4所示，该音频数据处理方法400包括在操作S401，判断音频数据(简称音频)中是否包含伴奏音乐(简称伴奏)。如果包含伴奏，则执行操作S402。如果只包含人声不包含伴奏，则执行操作S403。
在操作S402，利用声源分离算法将人声与伴奏分离。然后针对分离得到的人声执行操作S403。
在操作S403，对人声提取过零率、基频f0与能量。
在操作S404，基于过零率与能量对基频进行修正获得F0。
在操作S405，利用人声与修正后的基频F0计算频谱包络SP及非周期参数AP。
在操作S406，根据用户的设置的电音程度参数a和电音音调参数b，调整基频并获得F0′。
在操作S407，对基频F0′量化获得F0″。
在操作S408，使用基频F0″、频谱包络SP与非周期参数AP共同合成带有电音效果的人声。
在操作S409，如果音频带有伴奏，则执行操作S410。否则执行操作S411。
在操作S410，将伴奏也合入人声中，生成最终的带有电音效果的音频。
在操作S411，输出带有电音效果的音频。
根据本公开的实施例的音频数据处理方法，可以灵活且高效地为音频数据增加电音效果，提升用户的娱乐趣味性。
图5示意性示出了根据本公开实施例的音频数据处理装置的框图。
如图5所示，该音频数据处理装置500包括分解模块510、电音处理模块520和合成模块530。
分解模块510，用于分解原始音频数据，得到人声音频数据和背景音频数据。
电音处理模块520，用于对人声音频数据进行电音化处理，得到电音人声数据。
合成模块530，用于将电音人声数据和背景音频数据合成，得到目标音频数据。
根据本公开的实施例，分解模块可以包括梅尔频谱确定子模块、分解子模块和生成子模块。其中，梅尔频谱确定子模块，可以用于确定与原始音频数据对应的原始梅尔频谱数据。分解子模块，可以用于使用神经网络确定与原始梅尔频谱数据对应的背景梅尔频谱数据和人声梅尔频谱数据。生成子模块，可以用于根据背景梅尔频谱数据，生成背景音频数据，并根据人声梅尔频谱数据，生成人声音频数据。
根据本公开的实施例，电音处理模块可以包括提取子模块、修正子模块、调整子模块、量化子模块和电音确定子模块。其中，提取子模块，可以用于提取人声音频数 据的原始基频。修正子模块，可以用于对原始基频进行修正，得到第一基频。调整子模块，可以用于根据预定电音参数，调整第一基频，得到第二基频。量化子模块，可以用于针对第二基频进行量化处理，得到第三基频。电音确定子模块，可以用于根据第三基频，确定电音人声数据。
根据本公开的实施例，修正子模块可以包括：分段单元、能量确定单元、过零率确定单元、浊音判断单元和修正单元。其中，分段单元，可以用于将人声音频数据分为多个音频片段。能量确定单元，可以用于针对多个音频片段中的每个音频片段，确定音频片段的能量。过零率确定单元，可以用于针对多个音频片段中的每个音频片段，确定音频片段的过零率。浊音判断单元，可以用于根据能量和过零率，确定音频片段的类型是否为浊音音频片段。修正单元，可以用于利用线性插值算法，对浊音音频片段的基频进行修正。
根据本公开的实施例，音频片段设置有多个采样点。能量确定单元还可以用于根据音频片段中每个采样点的数值，确定音频片段的能量。
根据本公开的实施例，过零率确定单元还可以用于确定音频片段中每两个相邻采样点的数值是否彼此符号相反，然后确定音频片段中相邻采样点为异号的次数占所有采样点个数的比值，作为过零率。
根据本公开的实施例，预定电音参数可以包括电音程度参数和/或电音音调参数。调整子模块可以包括第一确定单元、第二确定单元和调整单元。其中，第一确定单元，可以用于根据浊音音频片段的基频，确定基频方差和/或基频平均值。第二确定单元，可以用于根据电音程度参数和基频方差，确定修正基频方差，以及/或者，根据电音程度参数和基频平均值，确定修正基频平均值。调整单元，可以用于根据修正基频方差和/或修正基频平均值，调整第一基频，得到第二基频。
根据本公开的实施例，量化子模块可以包括频率范围确定单元和第三基频确定单元。
其中，频率范围确定单元，可以用于根据以下公式确定频率范围：
Figure PCTCN2022082305-appb-000006
其中，scale为频率范围，F0′为第二基频。
第三基频确定单元，可以用于基于频率范围，根据以下公式确定第三基频：
Figure PCTCN2022082305-appb-000007
其中，F0″为第三基频。
根据本公开的实施例，上述音频数据处理装置，还可以包括确定模块，可以用于根据人声音频数据和第一基频，确定频谱包络和非周期参数。
根据本公开的实施例，电音确定子模块还可以用于根据第三基频、频谱包络和非周期参数，确定电音人声数据。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图6示意性示出了可以用来实施本公开的实施例的示例电子设备600的框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图6所示，设备600包括计算单元601，其可以根据存储在只读存储器(ROM)602中的计算机程序或者从存储单元608加载到随机访问存储器(RAM)603中的计算机程序，来执行各种适当的动作和处理。在RAM 603中，还可存储设备600操作所需的各种程序和数据。计算单元601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
设备600中的多个部件连接至I/O接口605，包括：输入单元606，例如键盘、鼠标等；输出单元607，例如各种类型的显示器、扬声器等；存储单元608，例如磁盘、光盘等；以及通信单元609，例如网卡、调制解调器、无线通信收发机等。通信单元609允许设备600通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元601可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元601的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种 专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元601执行上文所描述的各个方法和处理，例如音频数据处理方法。例如，在一些实施例中，音频数据处理方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元608。在一些实施例中，计算机程序的部分或者全部可以经由ROM 602和/或通信单元609而被载入和/或安装到设备600上。当计算机程序加载到RAM 603并由计算单元601执行时，可以执行上文描述的音频数据处理方法的一个或多个步骤。备选地，在其他实施例中，计算单元601可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行音频数据处理方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多 个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (21)

  1. 一种音频数据处理方法，包括：
    分解原始音频数据，得到人声音频数据和背景音频数据；
    对所述人声音频数据进行电音化处理，得到电音人声数据；以及
    将所述电音人声数据和所述背景音频数据合成，得到目标音频数据。
  2. 根据权利要求1所述的方法，其中，所述分解原始音频数据，得到背景音频数据和人声音频数据，包括：
    确定与所述原始音频数据对应的原始梅尔频谱数据；
    使用神经网络确定与所述原始梅尔频谱数据对应的背景梅尔频谱数据和人声梅尔频谱数据；以及
    根据所述背景梅尔频谱数据，生成所述背景音频数据，并根据所述人声梅尔频谱数据，生成所述人声音频数据。
  3. 根据权利要求1所述的方法，其中，所述对所述人声音频数据进行电音化处理，得到电音人声数据，包括：
    提取所述人声音频数据的原始基频；
    对所述原始基频进行修正，得到第一基频；
    根据预定电音参数，调整所述第一基频，得到第二基频；
    针对所述第二基频进行量化处理，得到第三基频；以及
    根据所述第三基频，确定所述电音人声数据。
  4. 根据权利要求3所述的方法，其中，所述对所述原始基频进行修正，得到第一基频，包括：
    将所述人声音频数据分为多个音频片段；
    针对所述多个音频片段中的每个音频片段，确定所述音频片段的能量和过零率；
    根据所述能量和过零率，确定所述音频片段是否为浊音音频片段；以及
    利用线性插值算法，对所述浊音音频片段的基频进行修正。
  5. 根据权利要求4所述的方法，其中，所述音频片段设置有多个采样点；所述确定所述音频片段的能量包括：
    根据所述音频片段中每个采样点的数值，确定所述音频片段的能量。
  6. 根据权利要求4所述的方法，其中，所述音频片段包括多个采样点；所述确定所述音频片段的过零率包括：
    确定所述音频片段中每两个相邻采样点的数值是否彼此符号相反；以及
    确定所述音频片段中相邻采样点为异号的次数占所有采样点个数的比值，作为所述过零率。
  7. 根据权利要求4所述的方法，其中，所述预定电音参数包括电音程度参数和/或电音音调参数；所述根据预定电音参数，调整所述第一基频，得到第二基频，包括：
    根据所述浊音音频片段的基频，确定基频方差和/或基频平均值；
    根据所述电音程度参数和所述基频方差，确定修正基频方差，以及/或者，根据所述电音音调参数和所述基频平均值，确定修正基频平均值；以及
    根据所述修正基频方差和/或修正基频平均值，调整所述第一基频，得到所述第二基频。
  8. 根据权利要求3-7中任一项所述的方法，其中，所述针对所述第二基频进行量化处理，得到第三基频，包括：
    根据以下公式确定频率范围：
    Figure PCTCN2022082305-appb-100001
    其中，所述scale为所述频率范围，所述F0′为所述第二基频；
    基于所述频率范围，根据以下公式确定所述第三基频：
    Figure PCTCN2022082305-appb-100002
    其中，所述F0″为所述第三基频。
  9. 根据权利要求3-7中任一项所述的方法，还包括：根据所述人声音频数据和所述第一基频，确定频谱包络和非周期参数；
    其中，所述根据所述第三基频，确定所述电音人声数据，包括：
    根据所述第三基频、所述频谱包络和所述非周期参数，确定所述电音人声数据。
  10. 一种音频数据处理装置，包括：
    分解模块，用于分解原始音频数据，得到人声音频数据和背景音频数据；
    电音处理模块，用于对所述人声音频数据进行电音化处理，得到电音人声数据；以及
    合成模块，用于将所述电音人声数据和所述背景音频数据合成，得到目标音频数 据。
  11. 根据权利要求10所述的装置，其中，所述分解模块包括：
    梅尔频谱确定子模块，用于确定与所述原始音频数据对应的原始梅尔频谱数据；
    分解子模块，用于使用神经网络确定与所述原始梅尔频谱数据对应的背景梅尔频谱数据和人声梅尔频谱数据；以及
    生成子模块，用于根据所述背景梅尔频谱数据，生成所述背景音频数据，并根据所述人声梅尔频谱数据，生成所述人声音频数据。
  12. 根据权利要求10所述的装置，其中，所述电音处理模块包括：
    提取子模块，用于提取所述人声音频数据的原始基频；
    修正子模块，用于对所述原始基频进行修正，得到第一基频；
    调整子模块，用于根据预定电音参数，调整所述第一基频，得到第二基频；
    量化子模块，用于针对所述第二基频进行量化处理，得到第三基频；以及
    电音确定子模块，用于根据所述第三基频，确定所述电音人声数据。
  13. 根据权利要求12所述的装置，其中，所述修正子模块包括：
    分段单元，用于将所述人声音频数据分为多个音频片段；
    能量确定单元，用于针对所述多个音频片段中的每个音频片段，确定所述音频片段的能量；
    过零率确定单元，用于针对所述多个音频片段中的每个音频片段，确定所述音频片段的过零率；
    浊音判断单元，用于根据所述能量和过零率，确定所述音频片段的类型是否为浊音音频片段；以及
    修正单元，用于利用线性插值算法，对所述浊音音频片段的基频进行修正。
  14. 根据权利要求13所述的装置，其中，所述音频片段设置有多个采样点；所述能量确定单元还用于：
    根据所述音频片段中每个采样点的数值，确定所述音频片段的能量。
  15. 根据权利要求13所述的装置，其中，所述音频片段包括多个采样点；所述过零率确定单元还用于：
    确定所述音频片段中每两个相邻采样点的数值是否彼此符号相反；以及
    确定所述音频片段中相邻采样点为异号的次数占所有采样点个数的比值，作为所述过零率。
  16. 根据权利要求13所述的装置，其中，所述预定电音参数包括电音程度参数和/或电音音调参数；所述调整子模块包括：
    第一确定单元，用于根据所述浊音音频片段的基频，确定基频方差和/或基频平均值；
    第二确定单元，用于根据所述电音程度参数和所述基频方差，确定修正基频方差，以及/或者，根据所述电音程度参数和所述基频平均值，确定修正基频平均值；以及
    调整单元，用于根据所述修正基频方差和/或修正基频平均值，调整所述第一基频，得到所述第二基频。
  17. 根据权利要求12-16中任一项所述的装置，其中，所述量化子模块包括：
    频率范围确定单元，用于根据以下公式确定频率范围：
    Figure PCTCN2022082305-appb-100003
    其中，所述scale为所述频率范围，所述F0′为所述第二基频；
    第三基频确定单元，用于基于所述频率范围，根据以下公式确定所述第三基频：
    Figure PCTCN2022082305-appb-100004
    其中，所述F0″为所述第三基频。
  18. 根据权利要求12-16中任一项所述的装置，还包括：
    确定模块，用于根据所述人声音频数据和所述第一基频，确定频谱包络和非周期参数；
    其中，所述电音确定子模块还用于：
    根据所述第三基频、所述频谱包络和所述非周期参数，确定所述电音人声数据。
  19. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-9中任一项所述的方法。
  20. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行根据权利要求1-9中任一项所述的方法。
  21. 一种计算机程序产品，包括计算机程序/指令，其特征在于，该计算机程序/指令被处理器执行时实现权利要求1-9中任一项所述方法的步骤。
PCT/CN2022/082305 2021-08-24 2022-03-22 音频数据处理方法、装置、设备以及存储介质 Ceased WO2023024501A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/915,624 US20240212703A1 (en) 2021-08-24 2022-03-22 Method of processing audio data, device, and storage medium
JP2022560146A JP7465992B2 (ja) 2021-08-24 2022-03-22 オーディオデータ処理方法、装置、機器、記憶媒体及びプログラム
EP22773390.4A EP4167226B1 (en) 2021-08-24 2022-03-22 Audio data processing method and apparatus, and device and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110978065.3 2021-08-24
CN202110978065.3A CN113689837B (zh) 2021-08-24 2021-08-24 音频数据处理方法、装置、设备以及存储介质

Publications (1)

Publication Number Publication Date
WO2023024501A1 true WO2023024501A1 (zh) 2023-03-02

Family

ID=78582118

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/082305 Ceased WO2023024501A1 (zh) 2021-08-24 2022-03-22 音频数据处理方法、装置、设备以及存储介质

Country Status (5)

Country Link
US (1) US20240212703A1 (zh)
EP (1) EP4167226B1 (zh)
JP (1) JP7465992B2 (zh)
CN (1) CN113689837B (zh)
WO (1) WO2023024501A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113689837B (zh) * 2021-08-24 2023-08-29 北京百度网讯科技有限公司 音频数据处理方法、装置、设备以及存储介质
CN114449339B (zh) * 2022-02-16 2024-04-12 深圳万兴软件有限公司 背景音效的转换方法、装置、计算机设备及存储介质
CN115054915B (zh) * 2022-07-12 2026-03-20 北京字跳网络技术有限公司 环境音频播放方法、装置、存储介质以及电子设备
CN116312431B (zh) * 2023-03-22 2023-11-24 广州资云科技有限公司 电音基调控制方法、装置、计算机设备和存储介质
CN119922371A (zh) * 2023-10-31 2025-05-02 北京字跳网络技术有限公司 一种多媒体资源处理方法、装置、设备及存储介质

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004212473A (ja) * 2002-12-27 2004-07-29 Matsushita Electric Ind Co Ltd カラオケ装置及びカラオケ再生方法
CN103440862A (zh) * 2013-08-16 2013-12-11 北京奇艺世纪科技有限公司 一种语音与音乐合成的方法、装置以及设备
CN108417228A (zh) * 2018-02-02 2018-08-17 福州大学 乐器音色迁移下的人声音色相似性度量方法
CN108922506A (zh) * 2018-06-29 2018-11-30 广州酷狗计算机科技有限公司 歌曲音频生成方法、装置和计算机可读存储介质
CN111370019A (zh) * 2020-03-02 2020-07-03 字节跳动有限公司 声源分离方法及装置、神经网络的模型训练方法及装置
CN111899706A (zh) * 2020-07-30 2020-11-06 广州酷狗计算机科技有限公司 音频制作方法、装置、设备及存储介质
CN112086085A (zh) * 2020-08-18 2020-12-15 珠海市杰理科技股份有限公司 音频信号的和声处理方法、装置、电子设备和存储介质
CN212660311U (zh) * 2020-08-27 2021-03-05 深圳市十盏灯科技有限责任公司 具有耳返功能的k歌耳机
CN113689837A (zh) * 2021-08-24 2021-11-23 北京百度网讯科技有限公司 音频数据处理方法、装置、设备以及存储介质

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH04340600A (ja) * 1991-05-17 1992-11-26 Mitsubishi Electric Corp 音声復号化装置
JP3266819B2 (ja) * 1996-07-30 2002-03-18 株式会社エイ・ティ・アール人間情報通信研究所 周期信号変換方法、音変換方法および信号分析方法
KR0176623B1 (ko) * 1996-10-28 1999-04-01 삼성전자주식회사 연속 음성의 유성음부와 무성자음부의 자동 추출방법 및 장치
US6078880A (en) * 1998-07-13 2000-06-20 Lockheed Martin Corporation Speech coding system and method including voicing cut off frequency analyzer
US7567898B2 (en) * 2005-07-26 2009-07-28 Broadcom Corporation Regulation of volume of voice in conjunction with background sound
JP5085700B2 (ja) * 2010-08-30 2012-11-28 株式会社東芝 音声合成装置、音声合成方法およびプログラム
JP5589767B2 (ja) 2010-10-29 2014-09-17 ヤマハ株式会社 音声処理装置
JP5830364B2 (ja) 2011-12-01 2015-12-09 日本放送協会 韻律変換装置およびそのプログラム
CN111465982B (zh) 2017-12-12 2024-10-15 索尼公司 信号处理设备和方法、训练设备和方法以及程序
CN110164469B (zh) 2018-08-09 2023-03-10 腾讯科技（深圳）有限公司 一种多人语音的分离方法和装置
CN109166593B (zh) * 2018-08-17 2021-03-16 腾讯音乐娱乐科技（深圳）有限公司 音频数据处理方法、装置及存储介质
CN109346109B (zh) * 2018-12-05 2020-02-07 百度在线网络技术（北京）有限公司 基频提取方法和装置
JP7309155B2 (ja) 2019-01-10 2023-07-18 グリー株式会社 コンピュータプログラム、サーバ装置、端末装置及び音声信号処理方法
CN110706679B (zh) * 2019-09-30 2022-03-29 维沃移动通信有限公司 一种音频处理方法及电子设备
CN111243619B (zh) * 2020-01-06 2023-09-22 平安科技（深圳）有限公司 语音信号分割模型的训练方法、装置和计算机设备
CN111724757A (zh) * 2020-06-29 2020-09-29 腾讯音乐娱乐科技（深圳）有限公司 一种音频数据处理方法及相关产品
CN113178183B (zh) * 2021-04-30 2024-05-14 杭州网易云音乐科技有限公司 音效处理方法、装置、存储介质和计算设备
CN114360587A (zh) * 2021-12-27 2022-04-15 北京百度网讯科技有限公司 识别音频的方法、装置、设备、介质及产品

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004212473A (ja) * 2002-12-27 2004-07-29 Matsushita Electric Ind Co Ltd カラオケ装置及びカラオケ再生方法
CN103440862A (zh) * 2013-08-16 2013-12-11 北京奇艺世纪科技有限公司 一种语音与音乐合成的方法、装置以及设备
CN108417228A (zh) * 2018-02-02 2018-08-17 福州大学 乐器音色迁移下的人声音色相似性度量方法
CN108922506A (zh) * 2018-06-29 2018-11-30 广州酷狗计算机科技有限公司 歌曲音频生成方法、装置和计算机可读存储介质
CN111370019A (zh) * 2020-03-02 2020-07-03 字节跳动有限公司 声源分离方法及装置、神经网络的模型训练方法及装置
CN111899706A (zh) * 2020-07-30 2020-11-06 广州酷狗计算机科技有限公司 音频制作方法、装置、设备及存储介质
CN112086085A (zh) * 2020-08-18 2020-12-15 珠海市杰理科技股份有限公司 音频信号的和声处理方法、装置、电子设备和存储介质
CN212660311U (zh) * 2020-08-27 2021-03-05 深圳市十盏灯科技有限责任公司 具有耳返功能的k歌耳机
CN113689837A (zh) * 2021-08-24 2021-11-23 北京百度网讯科技有限公司 音频数据处理方法、装置、设备以及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4167226A4

Also Published As

Publication number Publication date
EP4167226B1 (en) 2026-02-11
US20240212703A1 (en) 2024-06-27
EP4167226A4 (en) 2024-09-18
CN113689837B (zh) 2023-08-29
JP2023542760A (ja) 2023-10-12
JP7465992B2 (ja) 2024-04-11
EP4167226A1 (en) 2023-04-19
CN113689837A (zh) 2021-11-23

Similar Documents

Publication Publication Date Title
CN113689837B (zh) 音频数据处理方法、装置、设备以及存储介质
CN114141228B (zh) 语音合成模型的训练方法、语音合成方法和装置
KR102611024B1 (ko) 음성 합성 방법, 장치, 기기 및 컴퓨터 기록 매체
CN114495956B (zh) 语音处理方法、装置、设备及存储介质
WO2020215666A1 (zh) 语音合成方法、装置、计算机设备及存储介质
CN113963679B (zh) 一种语音风格迁移方法、装置、电子设备及存储介质
EP0970466A2 (en) Voice conversion system and methodology
EP4276822A1 (en) Method and apparatus for processing audio, electronic device and storage medium
CN112967732B (zh) 调整均衡器的方法、装置、设备和计算机可读存储介质
CN111261177A (zh) 语音转换方法、电子装置及计算机可读存储介质
CN113421584A (zh) 音频降噪方法、装置、计算机设备及存储介质
CN113160849A (zh) 歌声合成方法、装置及电子设备和计算机可读存储介质
Dinther et al. Perception of acoustic scale and size in musical instrument sounds
CN114203155A (zh) 训练声码器和语音合成的方法和装置
CN117672254A (zh) 语音转换方法、装置、计算机设备及存储介质
CN113889073A (zh) 语音处理方法、装置、电子设备和存储介质
CN119360810A (zh) 一种音乐生成方法及装置
CN114999440B (zh) 虚拟形象生成方法、装置、设备、存储介质以及程序产品
KR102611003B1 (ko) 음성 처리 방법, 장치, 기기 및 컴퓨터 기록 매체
CN116129839A (zh) 音频数据处理方法及装置、电子设备和介质
CN113066472A (zh) 合成语音处理方法及相关装置
CN118609598A (zh) 一种信息展示方法、装置及相关设备
US20230206943A1 (en) Audio recognizing method, apparatus, device, medium and product
CN114420141B (zh) 声码器的训练方法、装置、设备和存储介质
CN117542346A (zh) 一种语音评价方法、装置、设备及存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022560146

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2022773390

Country of ref document: EP

Effective date: 20220929

WWE Wipo information: entry into national phase

Ref document number: 17915624

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

WWG Wipo information: grant in national office

Ref document number: 2022773390

Country of ref document: EP