TW325542B - Phrase speech input method - Google Patents

Phrase speech input method

Info

Publication number
TW325542B
TW325542B TW083104988A TW83104988A TW325542B TW 325542 B TW325542 B TW 325542B TW 083104988 A TW083104988 A TW 083104988A TW 83104988 A TW83104988 A TW 83104988A TW 325542 B TW325542 B TW 325542B
Authority
TW
Taiwan
Prior art keywords
phrase
syllable
sub
speech
candidate
Prior art date
Application number
TW083104988A
Other languages
Chinese (zh)
Inventor
Jiunn-Fa Wang
Jyh-Shing Sheu
Tzong-Shiann Wu
Original Assignee
Jiunn-Fa Wang
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 Jiunn-Fa Wang filed Critical Jiunn-Fa Wang
Priority to TW083104988A priority Critical patent/TW325542B/en
Application granted granted Critical
Publication of TW325542B publication Critical patent/TW325542B/en

Links

Landscapes

  • Document Processing Apparatus (AREA)

Abstract

A phrase speech input method mainly comprises: (1) One syllable segmentation sub-system, which segments syllable initial and final by differentiating speech signal period stability level of initial and final into one series of speech frames, and sets speech characteristic parameter of each frame; (2) One speech recognition sub-system, which consists of one final Bayer^s network and one syllable Bayer^s network to recognize frame and generate candidate syllable; (3) One phrase-matching sub-system, which consists of one phrase-bank with link list data structure, and with the phrase-bank as base transforms candidate syllable into candidate phrase; (4) Featuring that system architecture and operation steps constituted by syllable segmentation sub-system, speech recognition sub-system, phrase-matching sub-system and user interface sub-system comprises: first from syllable segmentation sub-system segmenting speech signal of user input into initial and final, then from speech recognition sub-system generates syllable, then from phrase-matching sub-system according to candidate syllable characteristic selecting candidate phrase from phrase-bank with link list data structure.
TW083104988A 1994-05-31 1994-05-31 Phrase speech input method TW325542B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW083104988A TW325542B (en) 1994-05-31 1994-05-31 Phrase speech input method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW083104988A TW325542B (en) 1994-05-31 1994-05-31 Phrase speech input method

Publications (1)

Publication Number Publication Date
TW325542B true TW325542B (en) 1998-01-21

Family

ID=58262170

Family Applications (1)

Application Number Title Priority Date Filing Date
TW083104988A TW325542B (en) 1994-05-31 1994-05-31 Phrase speech input method

Country Status (1)

Country Link
TW (1) TW325542B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI508033B (en) * 2013-04-26 2015-11-11 Wistron Corp Method and device for learning language and computer readable recording medium
TWI836627B (en) * 2021-10-15 2024-03-21 賽微科技股份有限公司 Intelligent expansion similar word model system and method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI508033B (en) * 2013-04-26 2015-11-11 Wistron Corp Method and device for learning language and computer readable recording medium
US10102771B2 (en) 2013-04-26 2018-10-16 Wistron Corporation Method and device for learning language and computer readable recording medium
TWI836627B (en) * 2021-10-15 2024-03-21 賽微科技股份有限公司 Intelligent expansion similar word model system and method

Similar Documents

Publication Publication Date Title
EP0993197B1 (en) A method and an apparatus for the animation, driven by an audio signal, of a synthesised model of human face
MX9505299A (en) Systems, methods and articles of manufacture for performing high resolution n-best string hypothesization.
MY116482A (en) Distributed voice recognition system
EP2268036A3 (en) Video signal encoding and decoding method
EP0847041A3 (en) Method and apparatus for speech recognition performing noise adaptation
EP1255203A3 (en) Altering network transmitted content data based upon user specified characteristics
DE69915830D1 (en) IMPROVED METHOD FOR RECOVERING LOST DATA FRAME FOR LPC-BASED, PARAMETRIC LANGUAGE ENCODING SYSTEM.
CA2201516A1 (en) Method and system for a user to manually alter the quality of previously encoded video frames
MX9505296A (en) Speech recognition bias equalization method and apparatus.
CA2463230A1 (en) A method and apparatus for decoding handwritten characters
DE60007620D1 (en) SPEECH RECOGNITION PROCESS
IT1279171B1 (en) CONTINUOUS SPEECH RECOGNITION SYSTEM
AU2401500A (en) System and method for segmentation and recognition of speech signals
GB2343778B (en) Processing received data in a distributed speech recognition process
DE60126811D1 (en) CODING OF AUDIO SIGNALS
TW325542B (en) Phrase speech input method
EP0792502A4 (en) VERY SLOW BIT RATE VOICE MESSAGING SYSTEM USING ASYMMETRIC VOICE COMPRESSION PROCESSING
DE50208346D1 (en) METHOD FOR DETECTING LANGUAGE INFORMATION
KR20020031305A (en) Method for the encoding of prosody for a speech encoder working at very low bit rates
WO2002049004A3 (en) Speech recognition method and system for a small device
CN112581167A (en) Advertisement big data perception discernment storage terminal
WO2000026901A3 (en) Performing spoken recorded actions
WO1992006447A3 (en) Character recognition methods including separating and extractingparticular portions from extracted data
EP0770986A3 (en) Modified discrete word recognition
KR100322730B1 (en) Speaker adapting method