Movatterモバイル変換

[0]ホーム
URL:

FR2424589A1 - CONTINUOUS SPEECH RECOGNITION PROCESS - Google Patents

CONTINUOUS SPEECH RECOGNITION PROCESS

Info

Publication number
FR2424589A1
FR2424589A1FR7836328AFR7836328AFR2424589A1FR 2424589 A1FR2424589 A1FR 2424589A1FR 7836328 AFR7836328 AFR 7836328AFR 7836328 AFR7836328 AFR 7836328AFR 2424589 A1FR2424589 A1FR 2424589A1
Authority
FR
France
Prior art keywords
speech recognition
spectras
keywords
acoustic signal
continuous
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
FR7836328A
Other languages
French (fr)
Other versions
FR2424589B1 (en
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.)
Dialog Systems Inc
Original Assignee
Dialog Systems Inc
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
Priority claimed from US05/901,005external-prioritypatent/US4241329A/en
Priority claimed from US05/901,006external-prioritypatent/US4227177A/en
Application filed by Dialog Systems IncfiledCriticalDialog Systems Inc
Publication of FR2424589A1publicationCriticalpatent/FR2424589A1/en
Application grantedgrantedCritical
Publication of FR2424589B1publicationCriticalpatent/FR2424589B1/fr
Grantedlegal-statusCriticalCurrent

Links

Classifications

Landscapes

Abstract

Translated fromFrench

L'INVENTION CONCERNE LES PROCEDES DE RECONNAISSANCE DE PAROLE CONTINUE. ELLE SE RAPPORTE A UN PROCEDE DE DETECTION ET DE RECONNAISSANCE D'UN OU PLUSIEURS MOTS-CLES DANS UN SIGNAL ACOUSTIQUE CONTINU. CHAQUE MOT-CLE EST REPRESENTE PAR UN MODELE DE MOT-CLE REPRESENTANT UN OU PLUSIEURS DESSINS CIBLES CORRESPONDANT CHACUN A AU MOINS UN SPECTRE CHOISI PARMI PLUSIEURS SPECTRES DE DUREE REDUITE CREES SUIVANT UN SYSTEME PREDETERMINE, EN VUE DU TRAITEMENT DU SIGNAL ACOUSTIQUE RECU. LES SPECTRES SONT COMPARES A DES DESSINS CIBLES DES MODELES ET DES MOTS-CLES CANDIDATS SONT CHOISIS D'APRES UNE OPERATION PREDETERMINEE DE DECISION. LES TECHNIQUES DE CHAINE METTENT EN OEUVRE DES TESTS DE VRAISEMBLANCE ET PERMETTENT LE REJET DES FAUSSES ALARMES. APPLICATION AUX APPAREILS DE RECONNAISSANCE DE PAROLE.THE INVENTION RELATES TO CONTINUOUS SPEECH RECOGNITION METHODS. IT RELATES TO A PROCESS FOR DETECTION AND RECOGNITION OF ONE OR MORE KEYWORDS IN A CONTINUOUS ACOUSTIC SIGNAL. EACH KEYWORD IS REPRESENTED BY A KEYWORD MODEL REPRESENTING ONE OR MORE TARGET DRAWINGS EACH CORRESPONDING TO AT LEAST ONE SPECTRUM CHOSEN FROM SEVERAL SPECTRAS OF REDUCED DURATION CREATED FOLLOWING A PREDETERMINED SYSTEM, WITH A VIEW TO PROCESSING THE ACOUSTIC SIGNAL RECEIVED. SPECTRAS ARE COMPARED TO TARGET DRAWINGS CANDIDATE MODELS AND KEYWORDS ARE CHOSEN BASED ON A PREDETERMINED DECISION OPERATION. CHAIN TECHNIQUES IMPLEMENT TRUE-SIMILARITY TESTS AND ALLOW THE REJECTION OF FALSE ALARMS. APPLICATION TO SPEECH RECOGNITION DEVICES.

FR7836328A1978-04-271978-12-26 CONTINUOUS SPEECH RECOGNITION PROCESSGrantedFR2424589A1 (en)

Applications Claiming Priority (2)

Application NumberPriority DateFiling DateTitle
US05/901,005US4241329A (en)1978-04-271978-04-27Continuous speech recognition method for improving false alarm rates
US05/901,006US4227177A (en)1978-04-271978-04-27Continuous speech recognition method

Publications (2)

Publication NumberPublication Date
FR2424589A1true FR2424589A1 (en)1979-11-23
FR2424589B1 FR2424589B1 (en)1984-02-24

Family

ID=27129279

Family Applications (1)

Application NumberTitlePriority DateFiling Date
FR7836328AGrantedFR2424589A1 (en)1978-04-271978-12-26 CONTINUOUS SPEECH RECOGNITION PROCESS

Country Status (3)

CountryLink
JP (1)JPS54142910A (en)
FR (1)FR2424589A1 (en)
GB (4)GB1603926A (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
GB2179483B (en)*1985-08-201989-08-02Nat Res DevApparatus and methods for analysing data arising from conditions which can be represented by finite state machines
CN111369980B (en)*2020-02-272023-06-02网易有道信息技术(江苏)有限公司Voice detection method, device, electronic equipment and storage medium
CN118379992B (en)*2024-06-212024-08-27广州思正电子股份有限公司Speech recognition management system based on artificial intelligence

Citations (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US3943295A (en)*1974-07-171976-03-09Threshold Technology, Inc.Apparatus and method for recognizing words from among continuous speech

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US4038503A (en)*1975-12-291977-07-26Dialog Systems, Inc.Speech recognition apparatus

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US3943295A (en)*1974-07-171976-03-09Threshold Technology, Inc.Apparatus and method for recognizing words from among continuous speech

Also Published As

Publication numberPublication date
GB1603928A (en)1981-12-02
JPS6228479B2 (en)1987-06-20
JPS54142910A (en)1979-11-07
GB1603926A (en)1981-12-02
FR2424589B1 (en)1984-02-24
GB1603929A (en)1981-12-02
GB1603927A (en)1981-12-02

Similar Documents

PublicationPublication DateTitle
Mellinger et al.Recognizing transient low-frequency whale sounds by spectrogram correlation
Christie et al.Acoustics based terrain classification for legged robots
FR2520911B1 (en) ANALYSIS METHOD AND APPARATUS FOR SPEECH RECOGNITION
CN110992985A (en)Identification model determining method, identification method and identification system for identifying abnormal sounds of treadmill
FR2362387A1 (en) RAPID CELL ANALYSIS METHOD AND APPARATUS
FR2390795A1 (en) SPEECH RECOGNITION MACHINES
Stewart et al.Speech2spikes: Efficient audio encoding pipeline for real-time neuromorphic systems
EP2224425B1 (en)An audio signal processing system and autonomous robot having such system
Reddy et al.End-to-end pathological speech detection using wavelet scattering network
FR2424589A1 (en) CONTINUOUS SPEECH RECOGNITION PROCESS
Rahman et al.Hybrid system for automatic detection of gunshots in indoor environment
EP0473664A1 (en)Analysis of waveforms.
Al Bashit et al.Mfcc-based houston toad call detection using lstm
Alzahra et al.Bird sounds classification by combining PNCC and robust Mel-log filter bank features
Makropoulos et al.Convolutional recurrent neural networks for the classification of cetacean bioacoustic patterns
Simundsson et al.A neural network to classify auditory signals for use in autonomous harvester control systems
Andrić et al.Cepstrum-based analysis of radar Doppler signals
Kek et al.Acoustic scene classification using bilinear pooling on time-liked and frequency-liked convolution neural network
Palaniappan et al.Fuzzy ATRMAP classification of mental tasks using segmented and overlapped EEG signals
Szczodrak et al.Leveraging Activation Maps for Improved Acoustic Events Detection and Classification
SandholmDo orcas have semantic language? machine learning to predict orca behaviors using partially labeled vocalization data
Klinck et al.Detection of leopard seal (Hydrurga leptonyx) vocalizations using the Envelope-Spectrogram Technique (TEST) in combination with a Hidden Markov model
Mehta et al.Orca Call Detection using CNN and Spectrograms
Ruiz et al.Automated Detection of Cetaceans in Their Natural Habitats via R-CNN and Computer Vision Techniques
Jarnicki et al.Mobile object recognition based on acoustic information

Legal Events

DateCodeTitleDescription
STNotification of lapse
[8]ページ先頭
©2009-2025 Movatter.jp