ES2190342A1 - Metodo para identificacion de secuencias de audio. - Google Patents

Metodo para identificacion de secuencias de audio.

Info

Publication number
ES2190342A1
ES2190342A1 ES200101468A ES200101468A ES2190342A1 ES 2190342 A1 ES2190342 A1 ES 2190342A1 ES 200101468 A ES200101468 A ES 200101468A ES 200101468 A ES200101468 A ES 200101468A ES 2190342 A1 ES2190342 A1 ES 2190342A1
Authority
ES
Spain
Prior art keywords
identification
parameters
audio
sequences
abstract
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.)
Granted
Application number
ES200101468A
Other languages
English (en)
Other versions
ES2190342B1 (es
Inventor
I Mont Eloi Batlle
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.)
Universitat Pompeu Fabra UPF
Original Assignee
Universitat Pompeu Fabra UPF
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 Universitat Pompeu Fabra UPF filed Critical Universitat Pompeu Fabra UPF
Priority to ES200101468A priority Critical patent/ES2190342B1/es
Priority to PCT/ES2002/000312 priority patent/WO2003001508A1/es
Priority to EP02743274A priority patent/EP1439523A1/en
Publication of ES2190342A1 publication Critical patent/ES2190342A1/es
Application granted granted Critical
Publication of ES2190342B1 publication Critical patent/ES2190342B1/es
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

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
    • 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
    • G10L19/04—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 predictive techniques
    • G10L19/26—Pre-filtering or post-filtering
    • G10L19/265—Pre-filtering, e.g. high frequency emphasis prior to encoding
    • 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
    • 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]
    • 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
    • G10H2250/005—Algorithms for electrophonic musical instruments or musical processing, e.g. for automatic composition or resource allocation
    • G10H2250/015—Markov chains, e.g. hidden Markov models [HMM], for musical processing, e.g. musical analysis or musical composition
    • 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
    • G10H2250/005—Algorithms for electrophonic musical instruments or musical processing, e.g. for automatic composition or resource allocation
    • G10H2250/015—Markov chains, e.g. hidden Markov models [HMM], for musical processing, e.g. musical analysis or musical composition
    • G10H2250/021—Dynamic programming, e.g. Viterbi, for finding the most likely or most desirable sequence in music analysis, processing or composition

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Telephonic Communication Services (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

Método para identificación de secuencias de audio. Comprende las siguientes etapas; 1. preprocesado (602) de la secuencia de audio, comprendiendo las etapas de eliminación de las frecuencias superiores a un valor predeterminado con un filtro pasa-bajos, y de digitalización de la señal en un convertidor analógico/digital, 2. extracción de parámetros (301), representativos de la secuencia de audio, para obtener un vector de parámetros especialmente adaptado al enfoque de identificación propuesto, 3. cálculo de descriptores abstractos (302), representativos del vector de parámetros, implementados como Modelos Ocultos de Markov, optimizados mediante el uso de una base de datos de definición de descriptores abstractos (303) generada durante la ejecución previa de una primera fase en modo de aprendizaje del método, 4. identificación (605) de las secuencias de audio así tratadas en una base de datos de secuencias de descriptores abstractos (505) generada durante la ejecución previa de una segundafase en modo de aprendizaje del método.
ES200101468A 2001-06-25 2001-06-25 Metodo para identificacion de secuencias de audio. Expired - Fee Related ES2190342B1 (es)

Priority Applications (3)

Application Number Priority Date Filing Date Title
ES200101468A ES2190342B1 (es) 2001-06-25 2001-06-25 Metodo para identificacion de secuencias de audio.
PCT/ES2002/000312 WO2003001508A1 (es) 2001-06-25 2002-06-25 Método para identificación de secuencias de audio
EP02743274A EP1439523A1 (en) 2001-06-25 2002-06-25 Method for multiple access and transmission in a point-to-multipoint system on an electric network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
ES200101468A ES2190342B1 (es) 2001-06-25 2001-06-25 Metodo para identificacion de secuencias de audio.

Publications (2)

Publication Number Publication Date
ES2190342A1 true ES2190342A1 (es) 2003-07-16
ES2190342B1 ES2190342B1 (es) 2004-11-16

Family

ID=8498172

Family Applications (1)

Application Number Title Priority Date Filing Date
ES200101468A Expired - Fee Related ES2190342B1 (es) 2001-06-25 2001-06-25 Metodo para identificacion de secuencias de audio.

Country Status (3)

Country Link
EP (1) EP1439523A1 (es)
ES (1) ES2190342B1 (es)
WO (1) WO2003001508A1 (es)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112863541B (zh) * 2020-12-31 2024-02-09 福州数据技术研究院有限公司 一种基于聚类和中值收敛的音频切割方法和系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0805434A2 (en) * 1996-05-01 1997-11-05 Microsoft Corporation Method and system for speech recognition using continuous density hidden Markov models
EP0903728A2 (en) * 1997-09-19 1999-03-24 Nortel Networks Corporation Block algorithm for pattern recognition
US5890111A (en) * 1996-12-24 1999-03-30 Technology Research Association Of Medical Welfare Apparatus Enhancement of esophageal speech by injection noise rejection
US6182036B1 (en) * 1999-02-23 2001-01-30 Motorola, Inc. Method of extracting features in a voice recognition system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0805434A2 (en) * 1996-05-01 1997-11-05 Microsoft Corporation Method and system for speech recognition using continuous density hidden Markov models
US5890111A (en) * 1996-12-24 1999-03-30 Technology Research Association Of Medical Welfare Apparatus Enhancement of esophageal speech by injection noise rejection
EP0903728A2 (en) * 1997-09-19 1999-03-24 Nortel Networks Corporation Block algorithm for pattern recognition
US6182036B1 (en) * 1999-02-23 2001-01-30 Motorola, Inc. Method of extracting features in a voice recognition system

Also Published As

Publication number Publication date
WO2003001508A1 (es) 2003-01-03
WO2003001508B1 (es) 2004-07-08
EP1439523A1 (en) 2004-07-21
ES2190342B1 (es) 2004-11-16
WO2003001508A8 (es) 2004-08-12

Similar Documents

Publication Publication Date Title
WO2021032219A3 (zh) 基于深度学习的疾病分类编码方法、系统、设备及介质
DK1307833T3 (da) Fremgangsmåde til sögning i en lyddatabase
WO2002077873A3 (en) System, method and apparatus for conducting a phrase search
WO2002061632A3 (en) System, method and article of manufacture for extensions in a programming language capable of programming hardware architectures
EP0376501A3 (en) Speech recognition system
WO2004013777B1 (en) System and method of parallel pattern matching
WO2003020245A8 (en) Residual solvent extraction method and microparticles produced thereby
DE60130475D1 (de) Durchführung von kalkulationen des tabellenkalkulationstyps in einem datenbanksystem
DE3873337D1 (de) Aetzverfahren mittels gasplasma.
EA200400878A1 (ru) Новые эфиры флуоренкарбоновых кислот, способ их получения, а также их применение в качестве лекарственных средств
DE60139122D1 (de) Verfahren zur produktion von natürlichen medizin präparaten
CN101551998A (zh) 一组可以进行语音互动的装置以及其和人的语音互动方法
DE68921422D1 (de) Verfahren zur Herstellung eines polaren anisotropen Magnetes aus seltenen Erden.
ATE361334T1 (de) Verfahren zur herstellung von hochreinem polycarbonat
WO2005004002A3 (fr) Procede de traitement d’une sequence sonore, telle qu’un morceau musical
ES2190342A1 (es) Metodo para identificacion de secuencias de audio.
ATE333101T1 (de) Verfahren zur generierung von testersteuerungen
WO2004039991A3 (en) Method for producing esterified astaxanthin from esterified zeaxanthin
DE69924853D1 (de) Ein verfahren und system zur stimmenwahl
DE60308066D1 (de) Verfahren zur herstellung von hyperpolarisiertem 129xe
CN106372055B (zh) 一种人机自然语言交互中的语义相似处理方法及系统
EP1089221A3 (en) Spike-based hybrid computation
CN109905945A (zh) 一种舞厅灯光智能控制方法
DE69007424D1 (de) Verfahren zur Herstellung eines oxidischen Supraleiters.
NO982920D0 (no) FremgangsmÕte for koding av et lydsignal som digitaliseres med en lav samplingsfrekvens

Legal Events

Date Code Title Description
EC2A Search report published

Date of ref document: 20030716

Kind code of ref document: A1

FG2A Definitive protection

Ref document number: 2190342B1

Country of ref document: ES

FD2A Announcement of lapse in spain

Effective date: 20180807