JPS6488600A - Word voice recognition equipment based on monosyllabic enunciation - Google Patents

Word voice recognition equipment based on monosyllabic enunciation

Info

Publication number
JPS6488600A
JPS6488600A JP62246025A JP24602587A JPS6488600A JP S6488600 A JPS6488600 A JP S6488600A JP 62246025 A JP62246025 A JP 62246025A JP 24602587 A JP24602587 A JP 24602587A JP S6488600 A JPS6488600 A JP S6488600A
Authority
JP
Japan
Prior art keywords
syllabic
matching
sections
recognition
segmentation
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
JP62246025A
Other languages
Japanese (ja)
Inventor
Hideo Segawa
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.)
Toshiba Corp
Original Assignee
Toshiba 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 Toshiba Corp filed Critical Toshiba Corp
Priority to JP62246025A priority Critical patent/JPS6488600A/en
Publication of JPS6488600A publication Critical patent/JPS6488600A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE: To absorb failures of segmentation or syllabic sections to improve the word recognition rate by providing a word recognition part which recognizes words by DP(Dynamic programming) matching. CONSTITUTION: An acoustic processing part 2 outputs voice spectrum information to a single syllable recognition part 3 as acoustic information and outputs voice power information to a detection and segmentation part 4. This part 4 compares voice power information with one or plural prescribed threshold to detect the leading edge and the trailing edge of each syllabic section and segments acoustic features of individual syllabic sections. In the single syllable recognition part 3, a syllable dictionary 5 is used to recognize vowels in accordance with acoustic features, and syllables are recognized based on the result of this vowel recognition. When a syllabic category is identified, word recognition is next performed by DP matching. Since detection errors of syllabic sections in the detection and segmentation part can be absorbed by DP matching, the word recognition rate is considerably improved.
JP62246025A 1987-09-30 1987-09-30 Word voice recognition equipment based on monosyllabic enunciation Pending JPS6488600A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP62246025A JPS6488600A (en) 1987-09-30 1987-09-30 Word voice recognition equipment based on monosyllabic enunciation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP62246025A JPS6488600A (en) 1987-09-30 1987-09-30 Word voice recognition equipment based on monosyllabic enunciation

Publications (1)

Publication Number Publication Date
JPS6488600A true JPS6488600A (en) 1989-04-03

Family

ID=17142328

Family Applications (1)

Application Number Title Priority Date Filing Date
JP62246025A Pending JPS6488600A (en) 1987-09-30 1987-09-30 Word voice recognition equipment based on monosyllabic enunciation

Country Status (1)

Country Link
JP (1) JPS6488600A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0977175A2 (en) * 1998-07-27 2000-02-02 Canon Kabushiki Kaisha Method and apparatus for recognizing speech using a knowledge base

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0977175A2 (en) * 1998-07-27 2000-02-02 Canon Kabushiki Kaisha Method and apparatus for recognizing speech using a knowledge base
EP0977175A3 (en) * 1998-07-27 2000-08-09 Canon Kabushiki Kaisha Method and apparatus for recognizing speech using a knowledge base

Similar Documents

Publication Publication Date Title
US4284846A (en) System and method for sound recognition
DE3372552D1 (en) Speech recognition system
DE69937176D1 (en) Segmentation method to extend the active vocabulary of speech recognizers
GB1380502A (en) Systems for the synthesis of speech from alphanumeric data
CA2198306A1 (en) Method and apparatus for an improved language recognition system
ES8204347A1 (en) Word typewriter.
Sakaguchi et al. The effect of polarity inversion of speech on human perception and data hiding as an application
Chen et al. A hidden Markov model applied to Chinese four-tone recognition
JPS6488600A (en) Word voice recognition equipment based on monosyllabic enunciation
JPS6138479B2 (en)
JPS6316766B2 (en)
Ziółko et al. Statistics of diphones and triphones presence on the word boundaries in the Polish language. Applications to ASR
Daly Recognition of words from their spellings: Integration of multiple knowledge sources
JPH032319B2 (en)
JPS59121400A (en) Voice processor
Kitazawa et al. DP-matching: with or without phonemes?
Lee et al. Using acoustic and prosodic cues to correct Chinese speech repairs.
Baekgaard et al. The head system and its approach to rule based acoustic-phonetic recognition of speech.
JPS59185400A (en) Monosyllable sound recognition system
JP2737122B2 (en) Voice dictionary creation device
JPS58123596A (en) Voice recognition system jointly using auxiliary information
Nitta et al. Development of Japanese voice-activated word processor using isolated monosyllable recognition
JPH0585918B2 (en)
JPS61121167A (en) Audio word processor using divided utterance
JPS61256396A (en) Voice recognition equipment