IT1270919B - Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali - Google Patents

Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali

Info

Publication number
IT1270919B
IT1270919B ITTO930309A ITTO930309A IT1270919B IT 1270919 B IT1270919 B IT 1270919B IT TO930309 A ITTO930309 A IT TO930309A IT TO930309 A ITTO930309 A IT TO930309A IT 1270919 B IT1270919 B IT 1270919B
Authority
IT
Italy
Prior art keywords
recognition
speaker
neural networks
isolated words
corresponds
Prior art date
Application number
ITTO930309A
Other languages
English (en)
Inventor
Dario Albesano
Roberto Gemello
Franco Mana
Original Assignee
Cselt Centro Studi Lab Telecom
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 Cselt Centro Studi Lab Telecom filed Critical Cselt Centro Studi Lab Telecom
Priority to ITTO930309A priority Critical patent/IT1270919B/it
Publication of ITTO930309A0 publication Critical patent/ITTO930309A0/it
Priority to JP6109158A priority patent/JP2654917B2/ja
Priority to CA002122575A priority patent/CA2122575C/en
Priority to EP94106987A priority patent/EP0623914B1/en
Priority to DE69414752T priority patent/DE69414752T2/de
Priority to DE0623914T priority patent/DE623914T1/de
Priority to US08/238,319 priority patent/US5566270A/en
Publication of ITTO930309A1 publication Critical patent/ITTO930309A1/it
Application granted granted Critical
Publication of IT1270919B publication Critical patent/IT1270919B/it

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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/16—Speech classification or search using artificial neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Character Discrimination (AREA)
  • Image Analysis (AREA)
  • Machine Translation (AREA)

Abstract

IL METODO PER IL RICONOSCIMENTO DI PAROLE ISOLATE INDIPENDENTE DAL PARLATORE E' BASATO SU UN SISTEMA DI RICONOSCIMENTO IBRIDO, CHE FA USO DI RETI NEURALI, SFRUTTANDONE L'ELABORAZIONE PARALLELA PER MIGLIORARE IL RICONOSCIMENTO E OTTIMIZZARE IN TEMPO E MEMORIA IL SISTEMA, E CONSERVA ALCUNI ASPETTI CONSOLIDATI DELLE TECNICHE DI RICONOSCIMENTO.LE PAROLE INTERE SONO MODELLATE CON AUTOMI DEI MODELLI MARKOVIANI DEL TIPO SINISTRA-DESTRA CON RECURSIONE SUGLI STATI, OGNUNO DEI QUALI CORRISPONDE AD UNA PORZIONE ACUSTICA DELLA PAROLA, E IL RICONOSCIMENTO AVVIENE EFFETTUANDO UNA PROGRAMMAZIONE DINAMICA SECONDO L'ALGORITMO DI VITERBI SU TUTTI GLI AUTOMI PER TROVARE QUELLO CON PERCORSO DI COSTO MINIMO, A CUI CORRISPONDE LA PAROLA RICONOSCIUTA, LE PROBABILITA' DI EMISSIONE ESSENDO CALCOLATE CON UNA RETE NEURALE CON CONTROREAZIONE, ADDESTRATA IN MODO ORIGINALE, E LE PROBABILITA' DI TRANSIZIONE ESSENDO OPPORTUNAMENTE STIMATE.
ITTO930309A 1993-05-05 1993-05-05 Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali IT1270919B (it)

Priority Applications (7)

Application Number Priority Date Filing Date Title
ITTO930309A IT1270919B (it) 1993-05-05 1993-05-05 Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali
JP6109158A JP2654917B2 (ja) 1993-05-05 1994-04-26 ニューラル・ネットワークを使用する話者独立孤立単語音声認識システム
CA002122575A CA2122575C (en) 1993-05-05 1994-04-29 Speaker independent isolated word recognition system using neural networks
EP94106987A EP0623914B1 (en) 1993-05-05 1994-05-04 Speaker independent isolated word recognition system using neural networks
DE69414752T DE69414752T2 (de) 1993-05-05 1994-05-04 Sprecherunabhängiges Erkennungssystem für isolierte Wörter unter Verwendung eines neuronalen Netzes
DE0623914T DE623914T1 (de) 1993-05-05 1994-05-04 Sprecherunabhängiges Erkennungssystem für isolierte Wörter unter Verwendung eines neuronalen Netzes.
US08/238,319 US5566270A (en) 1993-05-05 1994-05-05 Speaker independent isolated word recognition system using neural networks

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
ITTO930309A IT1270919B (it) 1993-05-05 1993-05-05 Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali

Publications (3)

Publication Number Publication Date
ITTO930309A0 ITTO930309A0 (it) 1993-05-05
ITTO930309A1 ITTO930309A1 (it) 1994-11-05
IT1270919B true IT1270919B (it) 1997-05-16

Family

ID=11411463

Family Applications (1)

Application Number Title Priority Date Filing Date
ITTO930309A IT1270919B (it) 1993-05-05 1993-05-05 Sistema per il riconoscimento di parole isolate indipendente dal parlatore mediante reti neurali

Country Status (6)

Country Link
US (1) US5566270A (it)
EP (1) EP0623914B1 (it)
JP (1) JP2654917B2 (it)
CA (1) CA2122575C (it)
DE (2) DE623914T1 (it)
IT (1) IT1270919B (it)

Families Citing this family (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0728487A (ja) * 1993-03-26 1995-01-31 Texas Instr Inc <Ti> 音声認識方法
US5774846A (en) 1994-12-19 1998-06-30 Matsushita Electric Industrial Co., Ltd. Speech coding apparatus, linear prediction coefficient analyzing apparatus and noise reducing apparatus
US5687287A (en) * 1995-05-22 1997-11-11 Lucent Technologies Inc. Speaker verification method and apparatus using mixture decomposition discrimination
US5963903A (en) * 1996-06-28 1999-10-05 Microsoft Corporation Method and system for dynamically adjusted training for speech recognition
US6026359A (en) * 1996-09-20 2000-02-15 Nippon Telegraph And Telephone Corporation Scheme for model adaptation in pattern recognition based on Taylor expansion
US6167374A (en) * 1997-02-13 2000-12-26 Siemens Information And Communication Networks, Inc. Signal processing method and system utilizing logical speech boundaries
US5924066A (en) * 1997-09-26 1999-07-13 U S West, Inc. System and method for classifying a speech signal
ITTO980383A1 (it) * 1998-05-07 1999-11-07 Cselt Centro Studi Lab Telecom Procedimento e dispositivo di riconoscimento vocale con doppio passo di riconoscimento neurale e markoviano.
US6208963B1 (en) * 1998-06-24 2001-03-27 Tony R. Martinez Method and apparatus for signal classification using a multilayer network
DE19948308C2 (de) * 1999-10-06 2002-05-08 Cortologic Ag Verfahren und Vorrichtung zur Geräuschunterdrückung bei der Sprachübertragung
US7006969B2 (en) * 2000-11-02 2006-02-28 At&T Corp. System and method of pattern recognition in very high-dimensional space
US7369993B1 (en) 2000-11-02 2008-05-06 At&T Corp. System and method of pattern recognition in very high-dimensional space
US6662091B2 (en) 2001-06-29 2003-12-09 Battelle Memorial Institute Diagnostics/prognostics using wireless links
NZ530434A (en) 2001-07-02 2005-01-28 Battelle Memorial Institute Intelligent microsensor module
ITTO20020170A1 (it) 2002-02-28 2003-08-28 Loquendo Spa Metodo per velocizzare l'esecuzione di reti neurali per il riconoscimento della voce e relativo dispositivo di riconoscimento vocale.
EP1363271A1 (de) 2002-05-08 2003-11-19 Sap Ag Verfahren und System zur Verarbeitung und Speicherung von Sprachinformationen eines Dialogs
DE10220524B4 (de) 2002-05-08 2006-08-10 Sap Ag Verfahren und System zur Verarbeitung von Sprachdaten und zur Erkennung einer Sprache
GB2397664B (en) * 2003-01-24 2005-04-20 Schlumberger Holdings System and method for inferring geological classes
KR100883652B1 (ko) * 2006-08-03 2009-02-18 삼성전자주식회사 음성 구간 검출 방법 및 장치, 및 이를 이용한 음성 인식시스템
US8126262B2 (en) * 2007-06-18 2012-02-28 International Business Machines Corporation Annotating video segments using feature rhythm models
DE202008016880U1 (de) 2008-12-19 2009-03-12 Hörfabric GmbH Digitales Hörgerät mit getrennter Ohrhörer-Mikrofon-Einheit
US8700399B2 (en) 2009-07-06 2014-04-15 Sensory, Inc. Systems and methods for hands-free voice control and voice search
DE202010013508U1 (de) 2010-09-22 2010-12-09 Hörfabric GmbH Software-definiertes Hörgerät
US9015093B1 (en) 2010-10-26 2015-04-21 Michael Lamport Commons Intelligent control with hierarchical stacked neural networks
US8775341B1 (en) 2010-10-26 2014-07-08 Michael Lamport Commons Intelligent control with hierarchical stacked neural networks
CN102693723A (zh) * 2012-04-01 2012-09-26 北京安慧音通科技有限责任公司 一种基于子空间的非特定人孤立词识别方法及装置
US9627532B2 (en) * 2014-06-18 2017-04-18 Nuance Communications, Inc. Methods and apparatus for training an artificial neural network for use in speech recognition
US10825445B2 (en) 2017-03-23 2020-11-03 Samsung Electronics Co., Ltd. Method and apparatus for training acoustic model
US10255909B2 (en) 2017-06-29 2019-04-09 Intel IP Corporation Statistical-analysis-based reset of recurrent neural networks for automatic speech recognition
CN109902292B (zh) * 2019-01-25 2023-05-09 网经科技（苏州）有限公司 中文词向量处理方法及其系统
KR102152902B1 (ko) * 2020-02-11 2020-09-07 주식회사 엘솔루 음성 인식 모델을 학습시키는 방법 및 상기 방법을 이용하여 학습된 음성 인식 장치
CN114219669A (zh) * 2021-11-05 2022-03-22 招银云创信息技术有限公司 虚假信息识别方法、装置、计算机设备及可读存储介质
CN119204317A (zh) * 2024-09-12 2024-12-27 国网黑龙江省电力有限公司 基于bp神经网络模型和马尔可夫模型的绿色电力生产总量与结构预测模型

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB8908205D0 (en) * 1989-04-12 1989-05-24 Smiths Industries Plc Speech recognition apparatus and methods
GB8911461D0 (en) * 1989-05-18 1989-07-05 Smiths Industries Plc Temperature adaptors
GB2240203A (en) * 1990-01-18 1991-07-24 Apple Computer Automated speech recognition system

Also Published As

Publication number Publication date
JP2654917B2 (ja) 1997-09-17
CA2122575A1 (en) 1994-11-06
EP0623914A1 (en) 1994-11-09
ITTO930309A0 (it) 1993-05-05
EP0623914B1 (en) 1998-11-25
DE69414752D1 (de) 1999-01-07
DE623914T1 (de) 1995-08-24
US5566270A (en) 1996-10-15
ITTO930309A1 (it) 1994-11-05
DE69414752T2 (de) 1999-05-27
JPH06332497A (ja) 1994-12-02
CA2122575C (en) 1997-05-13

Similar Documents

Publication Publication Date Title
CA2122575A1 (en) Speaker Independent Isolated Word Recognition System Using Neural Networks
Young et al. Token passing: a simple conceptual model for connected speech recognition systems
Le et al. From senones to chenones: Tied context-dependent graphemes for hybrid speech recognition
Zhang et al. Attention based fully convolutional network for speech emotion recognition
CN112101044B (zh) 一种意图识别方法、装置及电子设备
CN113257248A (zh) 一种流式和非流式混合语音识别系统及流式语音识别方法
CN108492820A (zh) 基于循环神经网络语言模型和深度神经网络声学模型的中文语音识别方法
CN111429938A (zh) 一种单通道语音分离方法、装置及电子设备
WO2002101600A3 (en) Method for generating design constraints for modulates in a hierarchical integrated circuit design system
San-Segundo et al. Confidence measures for spoken dialogue systems
Pasupat et al. Span-based hierarchical semantic parsing for task-oriented dialog
Antoniol et al. Language model representations for beam-search decoding
Waterhouse et al. Ensemble methods for phoneme classification
Tian et al. Fsr: Accelerating the inference process of transducer-based models by applying fast-skip regularization
Atmaja et al. Jointly predicting emotion, age, and country using pre-trained acoustic embedding
Wyatt et al. A Privacy-Sensitive Approach to Modeling Multi-Person Conversations.
Dighe et al. Audio-to-intent using acoustic-textual subword representations from end-to-end asr
CN116416968A (zh) 一种由双编码器组成的transformer的重庆方言语音识别方法
DK0813734T3 (da) Fremgangsmåde til genkendelse af i det mindste ét defineret, ved hjælp af Hidden-Markov-modeller modelleret mønster i et ti
Mandal et al. Strategies for high accuracy keyword detection in noisy channels.
Djeffal et al. Transformer-based multi-head attention for noisy speech recognition
Meirong et al. Query-by-example on-device keyword spotting using convolutional recurrent neural network and connectionist temporal classification
Clarke et al. The modified Kanerva model: Theory and results for real-time word recognition
Zhu Development of wireless sensor device for machine English oral pronunciation noise detection
Łopatka et al. State sequence pooling training of acoustic models for keyword spotting

Legal Events

Date Code Title Description
0001 Granted