JPS6435600A - Section voice recognition - Google Patents

Section voice recognition

Info

Publication number
JPS6435600A
JPS6435600A JP62190474A JP19047487A JPS6435600A JP S6435600 A JPS6435600 A JP S6435600A JP 62190474 A JP62190474 A JP 62190474A JP 19047487 A JP19047487 A JP 19047487A JP S6435600 A JPS6435600 A JP S6435600A
Authority
JP
Japan
Prior art keywords
syllables
clause
recognition result
speech
syllable
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
JP62190474A
Other languages
Japanese (ja)
Inventor
Yasuhiro Nara
Hiroshi Tanaka
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.)
Fujitsu Ltd
Original Assignee
Fujitsu 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 Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP62190474A priority Critical patent/JPS6435600A/en
Publication of JPS6435600A publication Critical patent/JPS6435600A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE: To recognize a clause by a technique at a level of recognizing vocabulary of about 10000 words by narrowing down the number of syllables to be recognized by a start or end part and using a part-of-speech dictionary to select clause candidates which have grammatical meanings and have this number of syllables. CONSTITUTION: With respect to an inputted clause voice 8 consisting of L syllables S1 to SL, n syllables S1 to Sn in the start part and/or m syllables SL-m+1 to SL in the end part are recognized by blocks 9 and 10 to obtain a recognition result 15-1 or 15-2 as the result. Next, a part-of-speech dictionary 12 where grammar related to parts of speech is described together with their syllabic expressions is used to apply a part of speech corresponding to each syllable to the position of the syllable of the recognition result 15-1 (15-2) obtained by recognition operation, and one or plural clause candidates 16 having the same syllabic structure as the recognition result are generated. Canadidates 16 are collated with the clause voice 8 by the block 13 to obtain a final recognition result 14.
JP62190474A 1987-07-31 1987-07-31 Section voice recognition Pending JPS6435600A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP62190474A JPS6435600A (en) 1987-07-31 1987-07-31 Section voice recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP62190474A JPS6435600A (en) 1987-07-31 1987-07-31 Section voice recognition

Publications (1)

Publication Number Publication Date
JPS6435600A true JPS6435600A (en) 1989-02-06

Family

ID=16258713

Family Applications (1)

Application Number Title Priority Date Filing Date
JP62190474A Pending JPS6435600A (en) 1987-07-31 1987-07-31 Section voice recognition

Country Status (1)

Country Link
JP (1) JPS6435600A (en)

Similar Documents

Publication Publication Date Title
EP0801378A3 (en) Method and apparatus for speech recognition
EP0867858A3 (en) Pronunciation generation in speech recognition
PL335150A1 (en) Method of and apparatus for recognising spoken information
JPS6466698A (en) Voice recognition equipment
DE3856146T2 (en) Speech synthesis
CA2089786A1 (en) Context-dependent speech recognizer using estimated next word context
EP0241768A3 (en) Synthesizing word baseforms used in speech recognition
EP0285222A3 (en) Method for detecting associatively pronounced words
DE3853702T2 (en) Voice recognition.
DE3576868D1 (en) VOICE RECOGNITION.
JPS6435600A (en) Section voice recognition
Kvavik Research and pedagogical materials on Spanish intonation: A re-examination
WO2004008433A3 (en) System and method for mandarin chinese speech recognition using an optimized phone set
Furui Speech recognition-past, present, and future
Ainsworth et al. Connectionist architectures for a text-to-speech system.
Baekgaard et al. The head system and its approach to rule based acoustic-phonetic recognition of speech.
CN1051857C (en) Chinese phonetic entry method
Phillips Automatic discovery of acoustic measurements for phonetic classification
JPS56149640A (en) Voice input system
JPS6420599A (en) Japanese voice recognition equipment
JPS6437599A (en) Japanese sentence voice input device
EP0982712A3 (en) Segmentation technique increasing the active vocabulary of speech recognizers
Davies Hidden Markov Modelling of modern standard Chinese tones in connected speech
JPS59218547A (en) Kanji input device using speech recognition
Eady et al. A demisyllable-based text-to-speech synthesis system for English