JPS6437599A - Japanese sentence voice input device - Google Patents

Japanese sentence voice input device

Info

Publication number
JPS6437599A
JPS6437599A JP62194198A JP19419887A JPS6437599A JP S6437599 A JPS6437599 A JP S6437599A JP 62194198 A JP62194198 A JP 62194198A JP 19419887 A JP19419887 A JP 19419887A JP S6437599 A JPS6437599 A JP S6437599A
Authority
JP
Japan
Prior art keywords
phoneme
strings
dictionary
phonemic
phonemes
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
JP62194198A
Other languages
Japanese (ja)
Inventor
Tetsuo Araki
Jinichi Murakami
Satoru Ikehara
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.)
Nippon Telegraph and Telephone Corp
Original Assignee
Nippon Telegraph and Telephone 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 Nippon Telegraph and Telephone Corp filed Critical Nippon Telegraph and Telephone Corp
Priority to JP62194198A priority Critical patent/JPS6437599A/en
Publication of JPS6437599A publication Critical patent/JPS6437599A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE: To output a most likely candidate sequence out of sequences, which can exist as the Japanese language, with a high correct answer rate by using a phonemic chain probability dictionary with respect to phoneme candidate strings of recognition results from a voice recognition device. CONSTITUTION: A Japanese document expressed with the same kinds of phonemes as phoneme candidates recognized by a voice recognition device 1 is used to collect n-th-order phonemic chain probability values as connection probabilities between phonemes, and a dictionary 3 is generated which is indexed with each phonemic pattern as a key, and this dictionary is used to automatically select the most likely phoneme sequence. That is, most appropriate phoneme strings are ranked and evaluated from connectable phoneme strings because strength of connection is expressed as continuous information by probability values. Thus, the performance for the correct answer rate of phoneme candidate strings is improved.
JP62194198A 1987-08-03 1987-08-03 Japanese sentence voice input device Pending JPS6437599A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP62194198A JPS6437599A (en) 1987-08-03 1987-08-03 Japanese sentence voice input device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP62194198A JPS6437599A (en) 1987-08-03 1987-08-03 Japanese sentence voice input device

Publications (1)

Publication Number Publication Date
JPS6437599A true JPS6437599A (en) 1989-02-08

Family

ID=16320583

Family Applications (1)

Application Number Title Priority Date Filing Date
JP62194198A Pending JPS6437599A (en) 1987-08-03 1987-08-03 Japanese sentence voice input device

Country Status (1)

Country Link
JP (1) JPS6437599A (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS59185400A (en) * 1983-04-06 1984-10-20 株式会社リコー Monosyllable sound recognition system
JPS60135999A (en) * 1983-12-26 1985-07-19 株式会社日立製作所 Voice recognition system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS59185400A (en) * 1983-04-06 1984-10-20 株式会社リコー Monosyllable sound recognition system
JPS60135999A (en) * 1983-12-26 1985-07-19 株式会社日立製作所 Voice recognition system

Similar Documents

Publication Publication Date Title
EP0801378A3 (en) Method and apparatus for speech recognition
JPS6466698A (en) Voice recognition equipment
DE3876379D1 (en) AUTOMATIC DETERMINATION OF LABELS AND MARKOV WORD MODELS IN A VOICE RECOGNITION SYSTEM.
DE3778579D1 (en) TRAINING OF MARKOV MODELS RELATED TO A VOICE RECOGNITION SYSTEM.
DE69330427D1 (en) VOICE RECOGNITION SYSTEM FOR LANGUAGES WITH COMPOSED WORDS
DE69937176D1 (en) Segmentation method to extend the active vocabulary of speech recognizers
JPS57165900A (en) Voice recognition unit
EP0751467A3 (en) Translation apparatus and translation method
EP0755046A3 (en) Speech recogniser using a hierarchically structured dictionary
Veilleux et al. Probabilistic parse scoring with prosodic information
JPS6437599A (en) Japanese sentence voice input device
Sawai TDNN-LR continuous speech recognition system using adaptive incremental TDNN training
KR890010791A (en) Speech Recognition System for Voice Signal Search
JPS6229796B2 (en)
JPS6428699A (en) Continuous voice recognition system
DE3686651T2 (en) ACOUSTIC COMPARISON METHOD IN A VOICE RECOGNITION SYSTEM.
Kohda et al. Speech recognition in the question-answering system operated by conversational speech
JPS5729177A (en) Japanese voice input system
JPS6435600A (en) Section voice recognition
DE3681023D1 (en) DEVICE AND METHOD FOR VOICE RECOGNITION USING STATISTICAL WORD PATTERNS.
JPS5755480A (en) Voice typewriter
JPH0695689A (en) Speech recognition system
Doddington et al. High performance speaker‐independent word recognition
Ichikawa et al. Speaker verification from actual telephone voice
Hollien et al. Speaker identification: New vectors for SAUSI