JPS6481000A - Voice recognition equipment - Google Patents

Voice recognition equipment

Info

Publication number
JPS6481000A
JPS6481000A JP62238194A JP23819487A JPS6481000A JP S6481000 A JPS6481000 A JP S6481000A JP 62238194 A JP62238194 A JP 62238194A JP 23819487 A JP23819487 A JP 23819487A JP S6481000 A JPS6481000 A JP S6481000A
Authority
JP
Japan
Prior art keywords
learning
values
calculation
consonant
reference pattern
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.)
Pending
Application number
JP62238194A
Other languages
Japanese (ja)
Inventor
Yoshiyuki Niwa
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.)
Brother Industries Ltd
Original Assignee
Brother Industries Ltd
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 Brother Industries Ltd filed Critical Brother Industries Ltd
Priority to JP62238194A priority Critical patent/JPS6481000A/en
Publication of JPS6481000A publication Critical patent/JPS6481000A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE: To improve a recognition rate by the small quantity of calculation by providing the voice recognition device with a learning part for changing the start and end frames of a reference pattern registered in a storage part by learning. CONSTITUTION: A voice inputted from a voice input part 1 is segmented to consonant parts and vowel parts in each single sound by a segmentation part 2, feature parameters are calculated by an analysis part 3 and a matching part 5 executes soft matching based upon the calculated values, the segmented values, and calculation values and segmentation values stored in a reference pattern storing part 4. Then jdugement part 6 judges the existence of misrecognition by comparing the inputted data with the characters of a correct answer inputted by a teacher, and when misrecognition exists, learning is executed at least by a learning part 7. Thereby the frame length of the reference pattern is optimized by learning and only the consonant start frame and consonant end frame of the reference patterns are changed. Consequently the quantity of calculation is extremely reduced and the recognition rate is improved.
JP62238194A 1987-09-22 1987-09-22 Voice recognition equipment Pending JPS6481000A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP62238194A JPS6481000A (en) 1987-09-22 1987-09-22 Voice recognition equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP62238194A JPS6481000A (en) 1987-09-22 1987-09-22 Voice recognition equipment

Publications (1)

Publication Number Publication Date
JPS6481000A true JPS6481000A (en) 1989-03-27

Family

ID=17026555

Family Applications (1)

Application Number Title Priority Date Filing Date
JP62238194A Pending JPS6481000A (en) 1987-09-22 1987-09-22 Voice recognition equipment

Country Status (1)

Country Link
JP (1) JPS6481000A (en)

Similar Documents

Publication Publication Date Title
Bahl et al. Acoustic Markov models used in the Tangora speech recognition system
JPS6466698A (en) Voice recognition equipment
DE3264367D1 (en) Speech recognition system and method
EP1083542A3 (en) A method and apparatus for speech detection
GB2242772B (en) Language training
DE3778579D1 (en) TRAINING OF MARKOV MODELS RELATED TO A VOICE RECOGNITION SYSTEM.
ATE203119T1 (en) LANGUAGE RECOGNITION SYSTEM FOR COMPOUND WORD LANGUAGES
ES2028863T3 (en) VOICE RECOGNITION INSTRUCTED BY THE ORDER.
DE68912397D1 (en) Speech recognition with speaker adaptation through learning process.
JPS6410317A (en) Interactive input/output processing system
CA2051602A1 (en) Method and apparatus for generating models of spoken words based on a small number of utterances
JPS6481000A (en) Voice recognition equipment
Kocsor et al. A nonlinearized discriminant analysis and its application to speech impediment therapy
Liberman In favor of some uncommon approaches to the study of speech
DE3875894D1 (en) Adaptive multivariable analyseeinrichtung.
JPS61249182A (en) Pattern recognizing and learning device
Paczolay et al. Real-time vocal tract length normalization in a phonological awareness teaching system
EP1096462A3 (en) Language learning
JPS6428697A (en) Voice recognition equipment
JPS6425288A (en) Character recognition device
JPS6448088A (en) Character practicing apparatus
Kohda et al. Speech recognition in the question-answering system operated by conversational speech
JPS6465600A (en) Unspecified speaker voice recognition equipment
KR940024661A (en) Speech recognition method with limited duration of discrimination voice
JPS6437675A (en) Information recognizing device