CA2016342A1 - Methode de reconnaissance de formes utilisant des formes de reference definies chacune par des modeles d'etat - Google Patents

Methode de reconnaissance de formes utilisant des formes de reference definies chacune par des modeles d'etat

Info

Publication number
CA2016342A1
CA2016342A1 CA2016342A CA2016342A CA2016342A1 CA 2016342 A1 CA2016342 A1 CA 2016342A1 CA 2016342 A CA2016342 A CA 2016342A CA 2016342 A CA2016342 A CA 2016342A CA 2016342 A1 CA2016342 A1 CA 2016342A1
Authority
CA
Canada
Prior art keywords
sequence
feature vectors
reference patterns
time sequence
vectors
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
CA2016342A
Other languages
English (en)
Other versions
CA2016342C (fr
Inventor
Ken-Ichi Iso
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.)
NEC Corp
Original Assignee
NEC Corp
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 NEC Corp filed Critical NEC Corp
Priority to CA002109916A priority Critical patent/CA2109916C/fr
Publication of CA2016342A1 publication Critical patent/CA2016342A1/fr
Application granted granted Critical
Publication of CA2016342C publication Critical patent/CA2016342C/fr
Anticipated expiration legal-status Critical
Expired - Lifetime 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/12—Speech classification or search using dynamic programming techniques, e.g. dynamic time warping [DTW]
    • 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)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Image Analysis (AREA)
CA002016342A 1989-05-10 1990-05-09 Methode de reconnaissance de formes utilisant des formes de reference definies chacune par des modeles d'etat Expired - Lifetime CA2016342C (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CA002109916A CA2109916C (fr) 1989-05-10 1990-05-09 Methode de reconnaissance de configurations utilisant des configurations de reference definies chacune par des modeles a etats

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP117706/1989 1989-05-10
JP1117706A JP2545982B2 (ja) 1989-05-10 1989-05-10 パターン認識方法および標準パターン学習方法

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CA002109916A Division CA2109916C (fr) 1989-05-10 1990-05-09 Methode de reconnaissance de configurations utilisant des configurations de reference definies chacune par des modeles a etats

Publications (2)

Publication Number Publication Date
CA2016342A1 true CA2016342A1 (fr) 1990-11-10
CA2016342C CA2016342C (fr) 1994-04-26

Family

ID=14718296

Family Applications (1)

Application Number Title Priority Date Filing Date
CA002016342A Expired - Lifetime CA2016342C (fr) 1989-05-10 1990-05-09 Methode de reconnaissance de formes utilisant des formes de reference definies chacune par des modeles d'etat

Country Status (4)

Country Link
EP (1) EP0397136B1 (fr)
JP (1) JP2545982B2 (fr)
CA (1) CA2016342C (fr)
DE (1) DE69029425T2 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5696877A (en) * 1990-05-10 1997-12-09 Nec Corporation Pattern recognition using a predictive neural network
JP2979711B2 (ja) * 1991-04-24 1999-11-15 日本電気株式会社 パターン認識方式および標準パターン学習方式
JPH0776880B2 (ja) * 1993-01-13 1995-08-16 日本電気株式会社 パターン認識方法および装置
ES3048289T3 (en) * 2018-11-15 2025-12-09 Essilor Int A method and system for determining parameters used to manufacture an optical article and a corresponding optical article
CN110532646B (zh) * 2019-08-09 2023-05-02 北京工商大学 基于自适应动态规划的湖库蓝藻水华预测方法

Also Published As

Publication number Publication date
EP0397136A3 (fr) 1992-09-23
CA2016342C (fr) 1994-04-26
EP0397136B1 (fr) 1996-12-18
DE69029425D1 (de) 1997-01-30
JPH02296298A (ja) 1990-12-06
EP0397136A2 (fr) 1990-11-14
DE69029425T2 (de) 1997-04-03
JP2545982B2 (ja) 1996-10-23

Similar Documents

Publication Publication Date Title
WO1997008685A3 (fr) Procede et systeme de reconnaissance de motifs bases sur la construction dynamique d'un sous-ensemble de vecteurs de reference
DE3264367D1 (en) Speech recognition system and method
CA2105842A1 (fr) Systeme de commande base sur un reseau neuronal
CA2066952A1 (fr) Reconnaissance vocale par un reseau neuronal adapte a la saisie des patrons
CA2228948A1 (fr) Reconnaissance de configurations
EP0387791A3 (fr) Procédé et dispositif pour la reconnaissance de suites temporelles de signaux avec apprentissage insensible aux variations du signal
MX9505296A (es) Metodo y aparato para el reconocimiento de la voz, con reduccion del ruido de polarizacion.
EP0361443A3 (fr) Procédé et système de codage de la parole basés sur la quantification vectorielle
GB9017600D0 (en) An assembly and method for binary tree-searched vector quanisation data compression processing
CA2158064A1 (fr) Traitement de la parole
JPS5722295A (en) Speaker recognizing system
EP0574936A3 (en) Method and apparatus for input classification using non-spherical neurons
CA2016342A1 (fr) Methode de reconnaissance de formes utilisant des formes de reference definies chacune par des modeles d'etat
EP0318858A3 (fr) Système pour la reconnaissance de mots enchaínés comprenant des réseaux de neurones disposés le long d'un axe des temps associé au signal
CA2113316A1 (fr) Methode et systeme de reconnaissance de formes
CA2109916A1 (fr) Methode de reconnaissance de configurations utilisant des configurations de reference definies chacune par des modeles a etats
US5287429A (en) High speed recognition of a string of words connected according to a regular grammar by DP matching
CA2000033A1 (fr) Unite de reconnaissance de paroles continues
DE733982T1 (de) Verfahren zur Beschleunigung der Ausführungsgeschwindigkeit Neuronalnetzwerken für korrelierte Signalverarbeitung
EP0328064A3 (en) Device for generating a reference pattern with a continuous probability density function derived from feature code occurrence probability distribution
Ma et al. Modeling the acquisition of counting with an associative network
KR910012982A (ko) 데이터 처리장치를 위한 특정데이터 선택방법
SU1553993A1 (ru) Устройство дл моделировани нейронной сети
Carpenter Neural network modules for adaptive resonance theory(ART) architectures.
EP0428449A3 (en) Method and apparatus for pattern recognition, especially for speaker-independent speech recognition

Legal Events

Date Code Title Description
EEER Examination request
MKEX Expiry