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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 13pp  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: US5278942: Speech coding apparatus having speaker dependent prototypes generated from nonuser reference data
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
13 pages

 
Inventor: Bahl, Lalit R.; Amawalk, NY
Bellegarda, Jerome R.; Goldens Bridge, NY
De Souza, Peter V.; Mahopac Falls, NY
Gopalakrishnan, Ponani S.; Croton-on-Hudson, NY
Nadas, Arthur J.; Rock Tavern, NY
Nahamoo, David; White Plains, 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: 1994-01-11 / 1991-12-05

Application Number: US1991000802678

IPC Code: Advanced: G10L 15/02; G10L 15/06; G10L 15/10; G10L 19/00;
IPC-7: G10L 9/02;

ECLA Code: G10L15/063; G10L15/02;

U.S. Class: Current: 704/200; 704/E15.004; 704/E15.008;
Original: 395/002;

Field of Search: 381/029-45 395/002

Priority Number:
1991-12-05  US1991000802678

Abstract:     A speech coding apparatus and method for use in a speech recognition apparatus and method. The value of at least one feature of an utterance is measured during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values. A plurality of prototype vector signals, each having at least one parameter value and a unique identification value are stored. The closeness of the feature vector signal is compared to the parameter values of the prototype vector signals to obtain prototype match scores for the feature value signal and each prototype vector signal. The identification value of the prototype vector signal having the best prototype match score is output as a coded representation signal of the feature vector signal. Speaker-dependent prototype vector signals are generated from both synthesized training vector signals and measured training vector signals. The synthesized training vector signals are transformed reference feature vector signals representing the values of features of one or more utterances of one or more speakers in a reference set of speakers. The measured training feature vector signals represent the values of features of one or more utterances of a new speaker/user not in the reference set.

Attorney, Agent or Firm: Schechter, Marc D. ;

Primary / Asst. Examiners: Fleming, Michael R.; Doerrler, Michelle

Maintenance Status: E2 Expired  Check current status

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

Designated Country: DE FR GB IT 

Family: Show 7 known family members

First Claim:
Show all 39 claims
We claim:     1. A speech coding apparatus comprising:
  • means for measuring the value of at least one feature of an utterance during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values;
  • means for storing a plurality of prototype vector signals, each prototype vector signal having at least one parameter value, each prototype vector signal having a unique identification value;
  • means for comparing the closeness of the feature value of a feature vector signal to the parameter values of the prototype vector signals to obtain prototype match scores for the feature vector signal and each prototype vector signal; and
  • means for outputting at least the identification value of the prototype vector signal having the best prototype match score as a coded representation signal of the feature vector signal;
  • characterized in that the apparatus further comprises:
  • means for storing a plurality of reference feature vector signals, each reference feature vector signal representing the value of at least one feature of one or more utterances of one or more speakers in a reference set of speakers during each of a plurality of successive time intervals;
  • means for storing a plurality of measured training feature vector signals, each measured training feature vector signal representing the value of at least one feature of one or more utterances of a speaker not in the reference set during each of a plurality of successive time intervals;
  • means for transforming at least one reference feature vector signal into a synthesized training feature vector signal; and
  • means for generating the prototype vector signals from both the measured training vector signals and from the synthesized training vector signal.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 33 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (33)   |   Backward references (5)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 16pp US4651289  1987-03 Maeda et al.  Tokyo Shibaura Denki Kabushiki Kaisha Pattern recognition apparatus and method for making same
Get PDF - 12pp US4751737  1988-06 Gerson et al.  Motorola Inc. Template generation method in a speech recognition system
Get PDF - 30pp US4817156  1989-03 Bahl et al.  International Business Machines Corporation Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker
Get PDF - 14pp US4829577  1989-05 Kuroda et al.  International Business Machines Corporation Speech recognition method
Get PDF - 45pp US4980918  1990-12 Bahl et al.  International Business Machines Corporation Speech recognition system with efficient storage and rapid assembly of phonological graphs
       
Foreign References: None

Other Abstract Info: DERABS G93-183932

Other References:
  • Tappert et al., "Fast Training Method for Speech Recognition Systems," IBM Technical Disclosure Bulletin, vol. 21, No. 8, Jan. 1979, pp. 3413-3414.
  • Bahl, L. R. et al. "Acoustic Markov Models Used In The Tangora Speech Recognition System." Proceedings of the 1988 IEEE International Conference on Acoustics, Speech, and Signal Processing, S11-3, pp. 497-500, Apr. 1988.
  • Bahl, L. R., et al. "Fast Algorithm for Deriving Acoustic Prototoypes for Automatic Speech Recognition." U.S. patent application Ser. No. 732,714, filed on Jul. 16, 1991.
  • Bahl, L. R., et al. "A Maximum Likelihood Approach to Continuous Speech Recognition." IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, pp. 179-190, Mar. 1983. (12 pages) Cited by 42 patents
  • Bahl, L. R., et al. "Metamorphic Transformations For Speech Recognition." , IBM Technical Disclosure Bulletin, vol. 33, No. 1A, Jun. 1990, pp. 291-292.
  • Bahl, L. R., et al. "Speaker Independent Label Coding Apparatus." U.S. patent application Ser. No. 673,810, filed Mar. 22, 1991.
  • Bahl, L. R., et al. "Vector Quantization Procedure For Speech Recognition Systems Using Discrete Parameter Phoneme-Based Markov Word Models." , IBM Technical Disclosure Bulletin, vol. 34, No. 7, Dec. 1989, pp. 340 and 341.
  • Hartigan, J. A. "The K-Means Algorithm." Clustering Algorithms, pp. 84-105, John Wiley & Sons, 1975.
  • Jelinek, F. "Continuous Speech Recognition By Statistical Methods." Proceedings of the IEEE, vol. 64, No. 4, pp. 532-556, Apr. 1976. (25 pages) Cited by 30 patents
  • Jelinek, F. "The Development of an Experimental Discrete Dictation Recognizer." Proceedings of the IEEE, vol. 73, No. 11, Nov. 1985, pp. 1116-1624.


  • 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