FI873567A - RAMJAEMFOERELSEFOERFARANDE FOER EN ORDIDENTIFIERING I OMGIVNINGAR MED HOEG BULLERNIVAO. - Google Patents

RAMJAEMFOERELSEFOERFARANDE FOER EN ORDIDENTIFIERING I OMGIVNINGAR MED HOEG BULLERNIVAO. Download PDF

Info

Publication number
FI873567A
FI873567A FI873567A FI873567A FI873567A FI 873567 A FI873567 A FI 873567A FI 873567 A FI873567 A FI 873567A FI 873567 A FI873567 A FI 873567A FI 873567 A FI873567 A FI 873567A
Authority
FI
Finland
Prior art keywords
energy
channel
representative
ramjaemfoerelsefoerfarande
ordidentifiering
Prior art date
Application number
FI873567A
Other languages
Finnish (fi)
Other versions
FI873567A0 (en
Inventor
Ira A Gerson
Brett L Lindsley
Original Assignee
Motorola 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 Motorola Inc filed Critical Motorola Inc
Publication of FI873567A0 publication Critical patent/FI873567A0/en
Publication of FI873567A publication Critical patent/FI873567A/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
    • G10L15/00—Speech recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Time-Division Multiplex Systems (AREA)

Abstract

Method and arrangement for a speech recognition system using channel bank information to represent speech. The method considers background noise included with the speech. The method includes determining three energy levels for each channel, the first representative of background noise energy (20), the second representative of the input frame energy (16) and the third representative of the word template frame energy (18). Values representing energy level differentials are assigned at each channel. If the second energy level is less than the first energy level, then a predetermined constant value is assigned at that particular channel. These values are combined to generate a distance measure depicting the similarity between the two frames.
FI873567A 1986-01-06 1987-08-18 RAMJAEMFOERELSEFOERFARANDE FOER EN ORDIDENTIFIERING I OMGIVNINGAR MED HOEG BULLERNIVAO. FI873567A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US81659886A 1986-01-06 1986-01-06
PCT/US1986/002826 WO1987004294A1 (en) 1986-01-06 1986-12-29 Frame comparison method for word recognition in high noise environments

Publications (2)

Publication Number Publication Date
FI873567A0 FI873567A0 (en) 1987-08-18
FI873567A true FI873567A (en) 1987-08-18

Family

ID=25221081

Family Applications (1)

Application Number Title Priority Date Filing Date
FI873567A FI873567A (en) 1986-01-06 1987-08-18 RAMJAEMFOERELSEFOERFARANDE FOER EN ORDIDENTIFIERING I OMGIVNINGAR MED HOEG BULLERNIVAO.

Country Status (5)

Country Link
EP (1) EP0255529A4 (en)
JP (1) JPS63502304A (en)
CA (1) CA1301338C (en)
FI (1) FI873567A (en)
WO (1) WO1987004294A1 (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4805218A (en) * 1987-04-03 1989-02-14 Dragon Systems, Inc. Method for speech analysis and speech recognition
EP0459362B1 (en) * 1990-05-28 1997-01-08 Matsushita Electric Industrial Co., Ltd. Voice signal processor
JP3033061B2 (en) * 1990-05-28 2000-04-17 松下電器産業株式会社 Voice noise separation device
KR950013551B1 (en) * 1990-05-28 1995-11-08 마쯔시다덴기산교 가부시기가이샤 Noise signal predictting dvice
DE69132749T2 (en) * 1990-05-28 2002-07-04 Matsushita Electric Industrial Co., Ltd. Device for speech signal processing for determining a speech signal in a noisy speech signal
DE69133085T2 (en) * 1990-05-28 2003-05-15 Matsushita Electric Industrial Co., Ltd. speech
US6937674B2 (en) * 2000-12-14 2005-08-30 Pulse-Link, Inc. Mapping radio-frequency noise in an ultra-wideband communication system
WO2012176199A1 (en) * 2011-06-22 2012-12-27 Vocalzoom Systems Ltd Method and system for identification of speech segments

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4052568A (en) * 1976-04-23 1977-10-04 Communications Satellite Corporation Digital voice switch
GB1569450A (en) * 1976-05-27 1980-06-18 Nippon Electric Co Speech recognition system
JPS58130393A (en) * 1982-01-29 1983-08-03 株式会社東芝 Voice recognition equipment
GB2137791B (en) * 1982-11-19 1986-02-26 Secr Defence Noise compensating spectral distance processor

Also Published As

Publication number Publication date
CA1301338C (en) 1992-05-19
FI873567A0 (en) 1987-08-18
WO1987004294A1 (en) 1987-07-16
EP0255529A4 (en) 1988-06-08
JPS63502304A (en) 1988-09-01
EP0255529A1 (en) 1988-02-10

Similar Documents

Publication Publication Date Title
DE3750314D1 (en) Speech processor.
KR920005022A (en) Fingerprint Control Method
DE3884880D1 (en) Cheap speech recognition device and method.
EP0313975A3 (en) Design and construction of a binary-tree system for language modelling
DE3688747D1 (en) OPTIMAL PROCEDURE FOR DATA RECORDING IN A VOICE RECOGNITION SYSTEM.
KR830009898A (en) Curved Forming Method
FI873567A0 (en) RAMJAEMFOERELSEFOERFARANDE FOER EN ORDIDENTIFIERING I OMGIVNINGAR MED HOEG BULLERNIVAO.
Dailey Adult learning and organizations.
DE3750199D1 (en) Continuous speech recognition system.
GB2188763A (en) Noise compensation in speech recognition
AU584130B2 (en) Apparatus and method for identifying spoken words
DE3570784D1 (en) Improved phonemic classification in speech recognition system
Gonzales Philippine English across generations: The sound system
Lashkari et al. NMF-based cepstral features for speech emotion recognition
DE3875894D1 (en) Adaptive multivariable analyseeinrichtung.
Toyota Developmental difference of semantic constraint in children's recognition memory.
Kenig et al. On the existence and boundary behavior of solutions to a class of nonlinear Dirichlet problems
JP2655637B2 (en) Voice pattern matching method
Storm et al. Breadth of meaning, informativeness, and superordination relations among selected emotion terms appearing early and later in development.
JPS6126095A (en) Automatic calculation of word-to-word distance
North Commentaries on the Epistle to the Romans 1532–1542. By THL Parker. Edinburgh, T. & T. Clark, 1986, Pp. xii+ 226. No price.
Marimont How can the deaf learn to speak? Some fundamental questions.
JPS5759288A (en) Character recognition device
Blake Context vs paired-associate formats in retarded and normal pupils' learning concept names.
Katsell Chekhov: A Study of the Major Stories and Plays

Legal Events

Date Code Title Description
MM Patent lapsed

Owner name: MOTOROLA, INC.