KR890010791A - Speech Recognition System for Voice Signal Search - Google Patents

Speech Recognition System for Voice Signal Search Download PDF

Info

Publication number
KR890010791A
KR890010791A KR1019880016203A KR880016203A KR890010791A KR 890010791 A KR890010791 A KR 890010791A KR 1019880016203 A KR1019880016203 A KR 1019880016203A KR 880016203 A KR880016203 A KR 880016203A KR 890010791 A KR890010791 A KR 890010791A
Authority
KR
South Korea
Prior art keywords
speech signal
receiving
transient
retrieving
retrieval
Prior art date
Application number
KR1019880016203A
Other languages
Korean (ko)
Other versions
KR0136608B1 (en
Inventor
마꼬또 아까바네
요이찌로 사꼬
아쯔노부 히라이와
Original Assignee
오오가 노리오
소니 가부시끼 가이샤
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 JP62310569A external-priority patent/JP2643202B2/en
Priority claimed from JP32330787A external-priority patent/JPH01165000A/en
Priority claimed from JP62331656A external-priority patent/JPH01170998A/en
Application filed by 오오가 노리오, 소니 가부시끼 가이샤 filed Critical 오오가 노리오
Publication of KR890010791A publication Critical patent/KR890010791A/en
Application granted granted Critical
Publication of KR0136608B1 publication Critical patent/KR0136608B1/en

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/04—Segmentation; Word boundary detection

Abstract

내용 없음No content

Description

음성 신호 검색용 음성 인식 시스템Speech Recognition System for Voice Signal Search

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

제1도는 본 발명에 따른 음성 인식 시스템 실시예의 블럭 다이어그램.1 is a block diagram of an embodiment of a speech recognition system in accordance with the present invention.

제2도는 입력 음성 신호 및 과도 검색 파라미터의 파형을 설명하는 도시도.2 is a diagram illustrating waveforms of an input speech signal and a transient search parameter.

제3도는 특징점 예의 도시도.3 is an illustration of feature points.

제4도는 제1도에서 도시된 정상 및 과도부분의 더욱 상세한 블럭 다이어그램.4 is a more detailed block diagram of the normal and transient portions shown in FIG.

Claims (5)

언어 스팩트럼 제공 및 입력 음성신호를 정확하게 분해하기 위한 입력 음성 신호를 수신하는 소리분해기 수단과 ; 과도 검색 피라미터를 유도하기 위한 상기 소리 분해 수단으로부터 상기 언어 스팩트럼을 수신하는 수단과, 2개의 계속적인 과도 검색 파라미터 사이에서 차분 발생을 위한 상기 과도 검색 파라미터를 수신하는 수단과 ; 상기 입력 음성 신호의 정상부분 검색을 위해 상기 차분을 수신하는 제1검색 수단과 ; 상기 음성 신호의 과도부분 검색을 위한 상기 차분을 수신하는 제2검색 수단을 구비하는 것을 특징으로하는 음성신호의 검색 상태용 시스템.Sound decomposer means for receiving an input speech signal for providing a language spectrum and accurately decomposing the input speech signal; Means for receiving said language spectrum from said sound decomposition means for deriving a transient search parameter, and means for receiving said transient search parameter for difference generation between two successive transient search parameters; First retrieving means for receiving the difference for retrieving a normal portion of the input speech signal; And second retrieving means for receiving said difference for retrieving a transient portion of said speech signal. 제1항에 있어서, 상기 비결정 부분은 상기 정상부분 또는 과도 부분중 어느 하나도 아닌것을 갖으며, 상기 입력 음성 신호의 비결정 부분 검색을 위해, 상기 제1검색 수단 및 제2검색 수단으로 부터 출력 신호를 수신하는 제3검색 수단을 구비하는 것을 특징으로하는 음성신호의 검색 상태용 시스템.2. The apparatus of claim 1, wherein the amorphous portion has neither the normal portion nor the transient portion, and outputs an output signal from the first and second retrieval means for retrieving an amorphous portion of the input speech signal. And a third retrieval means for receiving. 제1항에 있어서, 상기 과도 검색 피라미터의 피크 검색용 피크 검색 수단을 특징으로하는 음성신호의 검색 상태용 시스템.2. The system for retrieving voice signals according to claim 1, characterized in that a peak retrieval means for peak retrieval of said transient retrieval parameter. 다수의 청각 파라미터 및 상기 입력 음성 신호를 청각적으로 분해하기 위한 입력 음성 신호를 수신하는 제1수단과 ; 상기 청각 파라미터의 특징점 검색용 다수의 청각 파라미터를 수신하는 제2수단과 ; 상기 특징점에 기초로하여 각각 음성 세그먼트 범위후보에 따라 음성 범위 특징 및 음성 세그먼트 범위 후보를 아웃푸팅 및 발생용 제3수단과; 상기 음성 범위 특징 및 상기 음성 세그먼트 범위후보에 따라 상기 입력 음성 신호에서 음성의 범위 인식용 제4수단을 구비하는 것을 특징으로하는 음성 신호에서 음성의 범위 인식용 시스템.First means for receiving a plurality of auditory parameters and an input speech signal for acoustically resolving the input speech signal; Second means for receiving a plurality of auditory parameters for feature point retrieval of the auditory parameter; Third means for outputting and generating the voice range feature and the voice segment range candidate according to the voice segment range candidates respectively based on the feature points; And fourth means for recognizing a range of voices in the input voice signal in accordance with the voice range feature and the voice segment range candidates. 제4항에 있어서, 다수의 청각 파라미터는 과도 검색 파라미터의 피크점을 검색하는 제2수단, 상기 검색된 피크점으로부터 예정된 주기에 따라 음성 범위 특징 및 상기 음성 세그먼트 범위 후보 아웃푸팅 및 발생의 제3수단을 구비하는 것을 특징으로하는 음성 신호내에서 음성의 범위 인식용시스템.5. The apparatus of claim 4, wherein the plurality of auditory parameters comprise: second means for searching for a peak point of a transient search parameter; A system for recognizing a range of speech within a speech signal, comprising: a speech signal; ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019880016203A 1987-12-08 1988-12-06 Phoneme recognizing device for voice signal status detection KR0136608B1 (en)

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
JP62310569A JP2643202B2 (en) 1987-12-08 1987-12-08 Detection device for steady, transient and uncertain parts of input speech
JP310569 1987-12-08
JP32330787A JPH01165000A (en) 1987-12-21 1987-12-21 Vocal sound section information forming apparatus
JP323307 1987-12-21
JP331656 1987-12-25
JP62331656A JPH01170998A (en) 1987-12-25 1987-12-25 Phoneme section information generating device

Publications (2)

Publication Number Publication Date
KR890010791A true KR890010791A (en) 1989-08-10
KR0136608B1 KR0136608B1 (en) 1998-11-16

Family

ID=27339113

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019880016203A KR0136608B1 (en) 1987-12-08 1988-12-06 Phoneme recognizing device for voice signal status detection

Country Status (5)

Country Link
KR (1) KR0136608B1 (en)
AU (1) AU612737B2 (en)
DE (1) DE3841376A1 (en)
FR (1) FR2624297B1 (en)
GB (1) GB2213623B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0538536A1 (en) * 1991-10-25 1993-04-28 International Business Machines Corporation Method for detecting voice presence on a communication line
DK46493D0 (en) * 1993-04-22 1993-04-22 Frank Uldall Leonhard METHOD OF SIGNAL TREATMENT FOR DETERMINING TRANSIT CONDITIONS IN AUDITIVE SIGNALS
ATE282879T1 (en) * 1998-03-13 2004-12-15 Frank Uldall Leonhard SIGNAL PROCESSING METHOD FOR ANALYZING VOICE SIGNAL TRANSIENTS
DE10317502A1 (en) * 2003-04-16 2004-11-18 Daimlerchrysler Ag Evaluation method e.g. for analysis of sounds signals, evaluating sound signal, through band pass filter with sound signal is in frequency range of first band-pass filter
IT1403658B1 (en) 2011-01-28 2013-10-31 Universal Multimedia Access S R L PROCEDURE AND MEANS OF SCANDING AND / OR SYNCHRONIZING AUDIO / VIDEO EVENTS

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5782896A (en) * 1980-11-12 1982-05-24 Hitachi Ltd Continuous voice recognition system

Also Published As

Publication number Publication date
DE3841376A1 (en) 1989-06-22
AU612737B2 (en) 1991-07-18
KR0136608B1 (en) 1998-11-16
FR2624297B1 (en) 1992-01-24
GB8828532D0 (en) 1989-01-11
FR2624297A1 (en) 1989-06-09
GB2213623B (en) 1991-07-24
AU2661788A (en) 1989-06-22
GB2213623A (en) 1989-08-16

Similar Documents

Publication Publication Date Title
KR870009322A (en) Speaker array language recognition system
KR970707529A (en) SPEECH RECOGNITION FOR SPEECH RECOGNITION DEVICE AND SPEECH RECOGNITION DEVICE
ATE374421T1 (en) SEGMENTATION METHOD FOR EXPANDING THE ACTIVE VOCABULARY OF LANGUAGE RECOGNIZERS
KR960038734A (en) Method and apparatus for speech recognition
DE69427083T2 (en) VOICE RECOGNITION SYSTEM FOR MULTIPLE LANGUAGES
JPS6184694A (en) Dictionary learning system for voice recognition
KR890010791A (en) Speech Recognition System for Voice Signal Search
Price et al. Combining linguistic with statistical methods in modeling prosody
Zahariev et al. An approach to speech ambiguities eliminating using semantically-acoustical analysis
JPS597998A (en) Continuous voice recognition equipment
Roelands et al. Waveform similarity based overlap-add (WSOLA) for time-scale modification of speech: structures and evaluation.
KR900015062A (en) Voice recognition device
KR0173204B1 (en) Voice recognition method of mutated phoneme using tree of korean mutated voice aggregation
JPS6234200A (en) Conversation voice understanding system utilizing meter information
JP2757356B2 (en) Word speech recognition method and apparatus
JP2008107641A (en) Voice data retrieving apparatus
Kobayashi et al. Word boundary detection by pitch contours in an artificial language
JPH0333798A (en) Voice retrieving device
JPS6288026A (en) Text vocalizing device
JPH054676B2 (en)
KR100393196B1 (en) Apparatus and method for recognizing speech
Reddy Words into action II: A task-oriented system: Harpy is an experimental, continuous-speech recognition system that exploits a low-cost minicomputer
JPS6420599A (en) Japanese voice recognition equipment
KR970049417A (en) Audio file database construction method, search method and suitable device
JPH06175677A (en) Voice recognizing method

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20011219

Year of fee payment: 5

LAPS Lapse due to unpaid annual fee