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

 The Delphion Integrated View

  Buy Now:   Buy PDF- 79pp  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: US4718094: Speech recognition system
[ Derwent Title ]

Country: US United States of America

View Images High


79 pages

Inventor: Bahl, Lalit R.; Amawalk, NY
deSouza, Peter V.; Yorktown Heights, NY
DeGennaro, Steven V.; Pawling, NY
Mercer, Robert L.; Yorktown Heights, NY

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

Published / Filed: 1988-01-05 / 1986-03-27

Application Number: US1986000845155

IPC Code: Advanced: G10L 11/00; G10L 15/08; G10L 15/10; G10L 15/12; G10L 15/14; G10L 15/18;
IPC-7: G10L 5/00;

ECLA Code: G10L15/08; G10L15/14M; S10L15/14M1; S10L15/187;

U.S. Class: Current: 704/256; 704/240; 704/251; 704/252; 704/255; 704/E15.014; 704/E15.028;
Original: 381/043; 364/513.5;

Field of Search: 381/041-43 364/513,513.5

Priority Number:
1986-03-27  US1986000845155

Abstract:     Speech words are recognized by first recognizing each spectral vector identified by a label (feneme), then identifying the word by matching the string of labels against phones using simplified phone machines based on label and transition probabilities and Merkov chains. In one embodiment, a detailed acoustic match word score is combined with an approximate acoustic match word score to provide a total word score for a subject word. In another embodiment, a polling word score is combined with an acoustic match word score to provide a total word score for a subject word. The acoustic models employed in the acoustic matching may correspond, alternatively, to phonetic elements or to fenemes. Fenemes represent labels generated by an acoustic processor in response to a spoken input. Apparatus and method for determining word scores according to approximate acoustic matching and for determining word scores according to a polling methodology are disclosed.

Attorney, Agent or Firm: Block, Marc A. ;

Primary / Asst. Examiners: Kemeny, E. S.;

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

Related Applications:
Application Number Filed Patent Pub. Date  Title
US1984000672974 1984-11-19       
US1985000738930 1985-05-29       

Parent Case:

    This application is a continuation-in-part (CIP) of U.S. Ser. No. 06/672,974 filed Nov. 19, 1984, abandoned, by L. R. Bahl, S. V. DeGennaro, and R. L. Mercer; and U.S. Ser. No. 06/738,930 filed May 29, 1985, abandoned, by L. R. Bahl, P. V. deSouza, and R. L. Mercer.

Designated Country: DE FR GB IT 

Family: Show 11 known family members

First Claim:
Show all 97 claims
We claim:     1. In a speech recognition system which represents each vocabulary word or a portion thereof by at least one sequence of phones wherein each phone corresponds to a respective phone machine, each phone machine having associated therewith (a) a plurality of transitions and (b) actual label output probabilities, each actual label probability representing the probability that a subject label is generated at a given transition in the phone machine, a method of performing an acoustic match between phones and a string of labels produced by an acoustic processor in response to a speech input, the method comprising the steps of:
  • forming simplified phone machines which includes the step of replacing by a single specific value the actual label probabilities for a given label at all transitions at which the given label may be generated in a particular phone machine; and
  • determining the probability of a phone generating the labels in the string based on the simplified phone machine corresponding thereto.

Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 93 U.S. patent(s) that reference this one

U.S. References: Go to Result Set: All U.S. references   |  Forward references (93)   |   Backward references (19)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 15pp US3943295  1976-03 Martin et al.  Threshold Technology, Inc. Apparatus and method for recognizing words from among continuous speech
Get PDF - 13pp US4038503  1977-07 Moshier  Dialog Systems, Inc. Speech recognition apparatus
Get PDF - 27pp US4156868  1979-05 Levinson  Bell Telephone Laboratories, Incorporated Syntactic word recognizer
Get PDF - 13pp US4158750  1979-06 Sakoe et al.  Nippon Electric Co., Ltd. Speech recognition system with delayed output
Get PDF - 34pp US4277644  1981-07 Levinson  Bell Telephone Laboratories, Incorporated Syntactic continuous speech recognizer
Get PDF - 47pp US4319085  1982-03 Welch et al.  Threshold Technology Inc. Speech recognition apparatus and method
Get PDF - 15pp US4348553  1982-09 Baker et al.  International Business Machines Corporation Parallel pattern verifier with dynamic time warping
Get PDF - 34pp US4400788  1983-08 Myers et al.  Bell Telephone Laboratories, Incorporated Continuous speech pattern recognizer
Get PDF - 23pp US4435617  1984-03 Griggs   Speech-controlled phonetic typewriter or display device using two-tier approach
Get PDF - 29pp US4467437  1984-08 Tsuruta et al.  Nippon Electric Co., Ltd. Pattern matching device with a DP technique applied to feature vectors of two information compressed patterns
Get PDF - 27pp US4481593  1984-11 Bahler  Exxon Corporation Continuous speech recognition
Get PDF - 26pp US4489434  1984-12 Moshier  Exxon Corporation Speech recognition method and apparatus
Get PDF - 24pp US4489435  1984-12 Moshier  Exxon Corporation Method and apparatus for continuous word string recognition
Get PDF - 9pp US4513436  1985-04 Nose et al.  Oki Electric Industry, Co., Ltd. Speech recognition system
Get PDF - 8pp US4516215  1985-05 Hakaridani et al.  Sharp Kabushiki Kaisha Recognition of speech or speech-like sounds
Get PDF - 15pp US4559604  1985-12 Ichikawa et al.  Hitachi, Ltd. Pattern recognition method
Get PDF - 20pp US4587670  1986-05 Levinson et al.  AT&T Bell Laboratories Hidden Markov model speech recognition arrangement
Get PDF - 28pp US4593367  1986-01 Slack et al.  ITT Corporation Probabilistic learning element
Get PDF - 11pp US4618983  1986-10 Nishioka et al.  Sharp Kabushiki Kaisha Speech recognition with preliminary matching
Foreign References: None

Other Abstract Info: DERABS G87-272491

Other References:
  • M. Cravero et al., "Phonetic Units for Hidden Markov Models", CSELT Technical Reports, vol., XIV, No. 2, Apr. 1986, pp. 121-125.
  • "Composite Fenemic Phones", Research Disclosure, Emsworth, Hampshire, GB., No. 256, Aug. 1985, pp. 418, Disclosed anonymously.
  • L. R. Rabiner et al., "Recognition of Isolated Digits using Hidden Markov Models with continuous Mixture Densities", AT&T Technical Journal, vol. 64, No. 6, Jul.-Aug. 1985, printed in U.S.A., pp. 1211-1234. (24 pages) Cited by 7 patents
  • H. Bourlard et al., "Speaker Dependent Connected Speech Recognition via Phonemic Markov Models", Proceedings of IEEE, 1985, pp. 1213-1216.
  • D. B. Paul, "Training of HMM Recognizers by Simulated Anealing", Proceedings of IEEE, 1985, pp. 13-16.
  • B. H. Juang et al., "Recent Developments in the Application of Hidden Markov Models to Speaker-Independent Isolated Word Recognition", Proceedings of IEEE, 1985, pp. 9-12.
  • Y. Kamp, "State Reduction in Hidden Markov Chains Used for Speech Recognition" IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-33, No. 4, Oct. 1985.
  • K. Sugawara et al., "Isolated Word Recognition Using Hidden Markov Models", Proceedings of IEEE, 1985, pp. 1-4.
  • R. Schwartz et al., "Context-Dependent Modeling for Acoustic-Phonetic Recognition of Continuous Speech", Proceedings of IEEE, 1985, pp. 1205-1208.
  • J. F. Mari et al., "Speaker Independent Connected Digit Recognition using _Hidden Markov Models", Speech Tech. 1985, pp. 127-132.
  • R. Schwartz et al., "Improved Hidden Markov Modeling of Phonemes for Continuous Speech Recognition", Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3 of 3, Mar. 19-21, 1984.
  • L. R. Bahl et al., "A Maximum Likelihood Approach to Continuous Speech Recognition", IEEE Transactions of Pattern Analysis and Machine Intelligence, vol., PAMI-5, No. 2, Mar. 1983.
  • F. Jelinek et al., "Design of a Linguistic Statistical Decoder for the Recognition of Continuous Speech", IEEE Transactions on Information Theory, vol., IT-21, No. 3, May 1975.
  • S. E. Levinson et al., "Speaker Independent Isolated Digit Recognition using Hidden Markov Models", Proceedings of IEEE, ICASSP 1983, Boston, pp. 1049-1052.
  • J. P. Haton, "Problems in the Design and Use of a Connected Speech Understanding System", Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 3 of 3, May 1982.
  • D. M. Choy et al., "Speech Compression by Phoneme Recognition", IBM Technical Disclosure Bulletin, vol. 25, No. 6, Nov. 1982, pp. 2884-2886.
  • L. R. Bahl et al., "Interpolation of Estimators Derived from Sparse Data", IBM Technical Disclosure Bulletin, vol. 24, No. 4, Sept. 1981, pp. 2038-2051.
  • L. R. Bahl et al., "Faster Acoustic Match Computation", IBM Technical Disclosure Bulletin, vol. 23, No. 4, Sept. 1980, pp. 1718-1719.
  • S. K. Das et al., "System for Temporal Regisration of Quasi-Phonemic Utterance Representations", IBM Technical Disclosure Bulletin, vol. 23, No. 7A, Dec. 1980. pp. 3047-3050.
  • R. W. A. Scarr, "Word-Recognition Machine", Proceedings of IEE, vol. 117, No. 1, Jan. 1987, pp. 203-212.

  • 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