[go: up one dir, main page]

TW373069B - Voiced/unvoiced noise of phonetic coding identifying method - Google Patents

Voiced/unvoiced noise of phonetic coding identifying method

Info

Publication number
TW373069B
TW373069B TW085115666A TW85115666A TW373069B TW 373069 B TW373069 B TW 373069B TW 085115666 A TW085115666 A TW 085115666A TW 85115666 A TW85115666 A TW 85115666A TW 373069 B TW373069 B TW 373069B
Authority
TW
Taiwan
Prior art keywords
value
voiced
frame
consonant
loh
Prior art date
Application number
TW085115666A
Other languages
Chinese (zh)
Inventor
Chin-Teng Lin
Xin-An Lin
Original Assignee
Holtek Semiconductor Inc
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 Holtek Semiconductor Inc filed Critical Holtek Semiconductor Inc
Priority to TW085115666A priority Critical patent/TW373069B/en
Priority to DE1997121684 priority patent/DE19721684A1/en
Application granted granted Critical
Publication of TW373069B publication Critical patent/TW373069B/en

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/78—Detection of presence or absence of voice signals

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

A kind of voiced/unvoiced noise of phonetic coding identifying method, it is preliminarily to input speech frame data into four sonic frames, then to identify each individual speech frame for execution of voiced/unvoiced noise. The method of identification comprises: to compare the regulated intersection related value of each of consonants separately with an upper limit temporary limit value and lower limit temporary limit value, to execute the judgement process for stable/unstable for judging the sizes of the capacity of the said consonant frame and LSP value, if the capacity value and LSP value are greater than the pre-set up temporary limit, then to execute the process of low pitch section of the said consonant frame to high pitch section capacity compared value LOH, in the judgement process of LOH to judge whether LOH value of every consonant frame is greater than the temporary limit value, if it is greater than the temporary limit value, it shall judge the consonant frame to be voiced speech signal; if no, then it shall judge the consonant frame to be unvoiced signal.
TW085115666A 1996-12-19 1996-12-19 Voiced/unvoiced noise of phonetic coding identifying method TW373069B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
TW085115666A TW373069B (en) 1996-12-19 1996-12-19 Voiced/unvoiced noise of phonetic coding identifying method
DE1997121684 DE19721684A1 (en) 1996-12-19 1997-05-23 Speech signal determination method for vocoder

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW085115666A TW373069B (en) 1996-12-19 1996-12-19 Voiced/unvoiced noise of phonetic coding identifying method

Publications (1)

Publication Number Publication Date
TW373069B true TW373069B (en) 1999-11-01

Family

ID=21625622

Family Applications (1)

Application Number Title Priority Date Filing Date
TW085115666A TW373069B (en) 1996-12-19 1996-12-19 Voiced/unvoiced noise of phonetic coding identifying method

Country Status (2)

Country Link
DE (1) DE19721684A1 (en)
TW (1) TW373069B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI566242B (en) * 2015-01-26 2017-01-11 宏碁股份有限公司 Speech recognition apparatus and speech recognition method
TWI576834B (en) * 2015-03-02 2017-04-01 聯詠科技股份有限公司 Method and apparatus for detecting noise of audio signals
US12066756B2 (en) 2018-09-27 2024-08-20 Taiwan Semiconductor Manufacturing Co., Ltd. Method for lithography process

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AT6920U1 (en) 2002-02-14 2004-05-25 Sail Labs Technology Ag METHOD FOR GENERATING NATURAL LANGUAGE IN COMPUTER DIALOG SYSTEMS

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI566242B (en) * 2015-01-26 2017-01-11 宏碁股份有限公司 Speech recognition apparatus and speech recognition method
TWI576834B (en) * 2015-03-02 2017-04-01 聯詠科技股份有限公司 Method and apparatus for detecting noise of audio signals
US12066756B2 (en) 2018-09-27 2024-08-20 Taiwan Semiconductor Manufacturing Co., Ltd. Method for lithography process

Also Published As

Publication number Publication date
DE19721684A1 (en) 1998-07-02

Similar Documents

Publication Publication Date Title
Ladd et al. The perception of intonational emphasis: continuous or categorical?
Caspers Local speech melody as a limiting factor in the turn-taking system in Dutch
Shriberg Phonetic consequences of speech disfluency
MX9605122A (en) Speech encoding method and apparatus and speech decoding method and apparatus.
Ljolje et al. Development of an acoustic-phonetic hidden Markov model for continuous speech recognition
EP0747883A3 (en) Voiced/unvoiced classification of speech for use in speech decoding during frame erasures
CA2413658A1 (en) System and method of spoken language understanding in human computer dialogs
Hawkins et al. Spread of CV and V-to-V coarticulation in British English: Implications for the intelligibility of synthetic speech
TW373069B (en) Voiced/unvoiced noise of phonetic coding identifying method
Maekawa Coarticulatory reinterpretation of allophonic variation: Corpus-based analysis of/z/in spontaneous Japanese
Lickley Juncture cues to disfluency
Torkkola Automatic alignment of speech with phonetic transcriptions in real time
Jang Automatic assessment of non-native prosody using rhythm metrics: Focusing on Korean speakers’ English pronunciation
Scharenborg et al. Segmentation of speech: Child's play?
Streefkerk et al. Automatic detection of prominence (as defined by listeners' judgements) in read aloud dutch sentences.
Diehl et al. Effect of Fundamental Frequency on Medial [+ Voice]/[–Voice] Judgments
Bennett et al. Prediction of pronunciation variations for speech synthesis: A data-driven approach
As-Sammer Phonetic and phonological adaptations of English loanwords into Iraqi Arabic: A generative study
Wang et al. Compressibility of segment duration in English and Chinese
O'Shaughnessy Analysis and automatic recognition of false starts in spontaneous speech
Hawkins et al. Sound to sense: Introduction to the special session
EP0984427A3 (en) Method for acoustically outputting text and speech output system
KR970050115A (en) Speech Recognition Method of Variation Unit using Korean Variation Grouping Tree
Kohlberger et al. Voicing assimilation in whispered speech
Peel et al. Reply to a Reply