KR930014267A - Speaker dependent speech recognition system and voice matching method - Google Patents

Speaker dependent speech recognition system and voice matching method Download PDF

Info

Publication number
KR930014267A
KR930014267A KR1019910025065A KR910025065A KR930014267A KR 930014267 A KR930014267 A KR 930014267A KR 1019910025065 A KR1019910025065 A KR 1019910025065A KR 910025065 A KR910025065 A KR 910025065A KR 930014267 A KR930014267 A KR 930014267A
Authority
KR
South Korea
Prior art keywords
speech recognition
recognition system
matching method
dependent speech
speaker dependent
Prior art date
Application number
KR1019910025065A
Other languages
Korean (ko)
Inventor
박정금
Original Assignee
백중영
금성통신 주식회사
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 백중영, 금성통신 주식회사 filed Critical 백중영
Priority to KR1019910025065A priority Critical patent/KR930014267A/en
Publication of KR930014267A publication Critical patent/KR930014267A/en

Links

Abstract

본 발명은 화자 종속 음성 인식 시스템 및 그의 음성 매칭 방법에 관한 것으로, 훈련 과정에 걸리는 시간을 줄이기 위하여 각 단어당 한번씩만 훈련하도록 하게 하는 화자 종속 음성 인식 시스템이다.The present invention relates to a speaker-dependent speech recognition system and a speech matching method thereof. The present invention relates to a speaker-dependent speech recognition system that allows training only once for each word in order to reduce the time required for the training process.

Description

화자종속 음성인식 시스템 및 그의 음성매칭 방법Speaker dependent speech recognition system and voice matching method

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음As this is a public information case, the full text was not included.

제1도는 음성 인식부의 블록도.1 is a block diagram of a speech recognition unit.

제3도는 본 발명에 따른 음성 매칭 방법의 개요도.3 is a schematic diagram of a speech matching method according to the present invention;

Claims (1)

화자 종속 음성 인식 시스템에 있어서, 훈련 과정에 걸리는 시간을 줄이기 위하여 각 단어당 한번씩만 훈련하도록 하게 하는 화자 종속 음성 인식 시스템.A speaker-dependent speech recognition system, wherein the speaker-dependent speech recognition system allows training only once for each word to reduce the time required for the training process. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019910025065A 1991-12-30 1991-12-30 Speaker dependent speech recognition system and voice matching method KR930014267A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019910025065A KR930014267A (en) 1991-12-30 1991-12-30 Speaker dependent speech recognition system and voice matching method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019910025065A KR930014267A (en) 1991-12-30 1991-12-30 Speaker dependent speech recognition system and voice matching method

Publications (1)

Publication Number Publication Date
KR930014267A true KR930014267A (en) 1993-07-22

Family

ID=67345919

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019910025065A KR930014267A (en) 1991-12-30 1991-12-30 Speaker dependent speech recognition system and voice matching method

Country Status (1)

Country Link
KR (1) KR930014267A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100230972B1 (en) * 1997-06-04 1999-11-15 서평원 Voice cognition service apparatus of full electronic exchange

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100230972B1 (en) * 1997-06-04 1999-11-15 서평원 Voice cognition service apparatus of full electronic exchange

Similar Documents

Publication Publication Date Title
DE69822179D1 (en) METHOD FOR LEARNING PATTERNS FOR VOICE OR SPEAKER RECOGNITION
DE69330427D1 (en) VOICE RECOGNITION SYSTEM FOR LANGUAGES WITH COMPOSED WORDS
DE68912397T2 (en) Speech recognition with speaker adaptation through learning process.
BR9814102A (en) System and process for representing complex information in auditory form
KR970707529A (en) SPEECH RECOGNITION FOR SPEECH RECOGNITION DEVICE AND SPEECH RECOGNITION DEVICE
DE3264367D1 (en) Speech recognition system and method
DE69937176D1 (en) Segmentation method to extend the active vocabulary of speech recognizers
DE68914449D1 (en) VOICE CONTROLLED OPERATION.
DE69022237D1 (en) Speech synthesis device based on the phonetic hidden Markov model.
BR9913524A (en) Voice recognizer, and, voice recognition process
ATE263997T1 (en) BETWEEN-WORDS CONNECTION PHONEMIC MODELS
KR930014267A (en) Speaker dependent speech recognition system and voice matching method
DE69908106D1 (en) EXTENSION OF A VOICE RECOGNITION Vocabulary Using Derived Words
Noss How useful are citation forms in synchronic Thai phonology
JPS4949241B1 (en)
Galiano et al. Experiments on Spanish Phone Recognition using automatically derived phonemic baseforms
KR970050120A (en) Speech Recognition Method in Word Spotting System
TW283774B (en) Intelligently vocal chinese input method and chinese dictation machine
KR970050115A (en) Speech Recognition Method of Variation Unit using Korean Variation Grouping Tree
TW265439B (en) Auto-labeling method for Chinese voice database phoneme for training purpose
DE69026795D1 (en) Speech recognition system with speech entry function, which is based on two utterances of each word
KR970056663A (en) 114 Information for improving voice data naturalness
KR900003814A (en) Speech Recognition System Using Two-Step Matching of Initial Pre-Matching
KR920008669A (en) Product description device using voice
KR970050108A (en) Accent generation method using accent pattern normalization and neural network learning in text / voice converter

Legal Events

Date Code Title Description
A201 Request for examination
N231 Notification of change of applicant
E902 Notification of reason for refusal
E601 Decision to refuse application