Work Files Saved Searches
   My Account                                                  Search:   Quick/Number   Boolean   Advanced       Help   

 The Delphion Integrated View

  Buy Now:   Buy PDF- 15pp  PDF  |   File History  |   Other choices   
  Tools:  Citation Link  |  Add to Work File:    
  View:  Expand Details   |  INPADOC   |  Jump to: 
 Email this to a friend  Email this to a friend 
Title: US5455889: Labelling speech using context-dependent acoustic prototypes
[ Derwent Title ]

Country: US United States of America

View Images High


15 pages

Inventor: Bahl, Lalit R.; Amawalk, NY
de Souza, Peter; San Jose, CA
Gopalakrishnan, P. S.; Yorktown Heights, NY
Picheny, Michael A.; White Plains, NY

Assignee: International Business Machines Corporation, Armonk, NY
other patents from INTERNATIONAL BUSINESS MACHINES CORPORATION (280070) (approx. 44,393)
 News, Profiles, Stocks and More about this company

Published / Filed: 1995-10-03 / 1993-02-08

Application Number: US1993000014966

IPC Code: Advanced: G10L 15/10; G10L 15/14; G10L 15/18; G10L 15/28; G10L 15/02;
IPC-7: G10L 5/06; G10L 9/00;

ECLA Code: G10L15/14M;

U.S. Class: Current: 704/236; 704/200; 704/231; 704/242; 704/243; 704/254; 704/256; 704/E15.028;
Original: 395/002.45; 395/002; 395/002.4; 395/002.51; 395/002.52; 395/002.65; 395/002.63;

Field of Search: 381/036-53 395/002,2.1-2.87

Priority Number:
1993-02-08  US1993000014966

Abstract:     The present invention relates to labelling of speech in a context-dependent speech recognition system. When labelling speech using context-dependent prototypes the phone context of a frame of speech needs to be aligned with the appropriate acoustic parameter vector. Since aligning a large amount of data is difficult if based upon arc ranks, the present invention aligns the data using context-independent acoustic prototypes. The phonetic context of each phone of the data is known. Therefore after the alignment step the acoustic parameter vectors are tagged with a corresponding phonetic context. Context-dependent prototype vectors exists for each label. For all labels the context-dependent prototype vectors having the same phonetic context as the tagged acoustic parameter vector are determined. For each label the probability of achieving the tagged acoustic parameter vector is determined given each of the context-dependent label prototype vectors having the same phonetic context as the tagged acoustic parameter vector. The label with the highest probability is associated with the context-dependent acoustic parameter vector.

Attorney, Agent or Firm: Tassinari, Jr., Robert P.Sterne, Kessler, Goldstein & Fox ;

Primary / Asst. Examiners: Downs, Robert W.; Hafiz, Tariq

Maintenance Status: E2 Expired  Check current status

INPADOC Legal Status: Show legal status actions          Buy Now: Family Legal Status Report

Family: Show 3 known family members

First Claim:
Show all 14 claims
Having thus described our invention, what we claim as new and desire to secure by Letters Patent is:     1. A computer based speech recognition system for labeling speech using context-dependent label prototype vectors, the system having an input comprising a sequence of phones from a training text, each of said sequence of phones having an associated phonetic context the system comprising:
  • a user interface configured to receive spoken sounds corresponding to a spoken version of the training text, and further configured to generate an outpt signal representative of said spoken sounds;
  • a signal processor, coupled to said user interface, configured to convert said output signal into a series of feature vector signals; and
  • a context-dependent labeller, coupled to said signal processor, configured to assign a context-dependent label to each feature vector signal of said series of feature vector signals to result in tagged feature vectors, comprising:
    • aligning means, coupled to said signal processor, for aligning each of said feature vector signals with a corresponding phone to result in aligned feature vector signals,
    • tagging means, coupled to said aligning means, for tagging each of said aligned feature vector signals with the phonetic context associated with said corresponding phone to result in tagged prototype vector signals, and
    • first associating means, coupled to said tagging means, for associating a label with each of said tagged prototype vector signals based upon a context-dependent prototype vector signal, comprising:
      • phonetic context identifying means for determining, for each said label, whether a context-dependent prototype vector signal exists corresponding to the phonetic context of the tagged prototype vector signal,
    • matching score generating means, coupled to said phonetic context identifying means, for generating a score for achieving said tagged feature vector signal given each of said context-dependent prototype vector signals having the same phonetic context as the tagged feature vector signal as determined in said phonetic context identifying means, and
    • associating means, coupled to said matching score generating means, for associating a label which is associated with a context-dependent prototype vector signal having the highest score as generated by said matching score generating means with said tagged feature vector signal.

Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 23 U.S. patent(s) that reference this one

U.S. References: Go to Result Set: All U.S. references   |  Forward references (23)   |   Backward references (7)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 20pp US4819271  1989-04 Bahl et al.  International Business Machines Corporation Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments
Get PDF - 67pp US4820059  1989-04 Miller et al.  Central Institute for the Deaf Speech processing apparatus and methods
Get PDF - 18pp US4933973  1990-06 Porter  ITT Corporation Apparatus and methods for the selective addition of noise to templates employed in automatic speech recognition systems
Get PDF - 50pp US4977599  1990-12 Bahl et al.  International Business Machines Corporation Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence
Get PDF - 9pp US5165007  1992-11 Bahl et al.  International Business Machines Corporation Feneme-based Markov models for words
Get PDF - 66pp US5168524  1992-12 Kroeker et al.  Eliza Corporation Speech-recognition circuitry employing nonlinear processing, speech element modeling and phoneme estimation
Get PDF - 59pp US5208897  1993-05 Hutchins  Emerson & Stern Associates, Inc. Method and apparatus for speech recognition based on subsyllable spellings
Foreign References: None

Other Abstract Info: DERABS G1995-351035 DERABS G1995-351035

Other References:
  • Schmidbauer et al, "An LVQ based reference model for speaker-adaptive speech recognition"; ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 441-444 vol. 1. 23-26 Mar. 1992.
  • Sehhati, "An interactive tool for segmentation and acoustic-phonetic analysis of speech SPANEX"; Sixth International Conference on Digital Processing of Signals in Communications, pp. 251-255, 2-6 Sep. 1991.
  • Kepuska et al, "Phonemic speech recognition system based on a neural network"; SOUTHEASTCON '89 Proceedings. Energy and Information Technologies in the Southeast, pp. 770-775 vol. 2. 9-12 Apr. 1989.

  • Inquire Regarding Licensing

    Powered by Verity

    Plaques from Patent Awards      Gallery of Obscure PatentsNominate this for the Gallery...

    Thomson Reuters Copyright © 1997-2014 Thomson Reuters 
    Subscriptions  |  Web Seminars  |  Privacy  |  Terms & Conditions  |  Site Map  |  Contact Us  |  Help