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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 50pp  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: US4977599: Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
50 pages

 
Inventor: Bahl, Lalit R.; Amawalk, NY
DeSouza, Peter V.; Yorktown Heights, NY
Mercer, Robert L.; 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: 1990-12-11 / 1988-12-15

Application Number: US1988000289447

IPC Code: Advanced: G10L 15/02; G10L 15/06; G10L 15/14;
IPC-7: G10L 5/04;

ECLA Code: G10L15/02; S10L15/063C; S10L15/14M;

U.S. Class: Current: 704/256.4; 704/243; 704/245; 704/E15.004;
Original: 381/043; 381/041;

Field of Search: 381/041-50 364/513,513.5

Priority Number:
1988-12-15  US1988000289447
1985-05-29  US1985000738912

Abstract:     Apparatus and method for constructing word baseforms which can be matched against a string of generated acoustic labels. A set of phonetic phone machines are formed, wherein each phone machine has (i) a plurality of states, (ii) a plurality of transitions each of which extends from a state to a state, (iii) a stored probability for each transition, and (iv) stored label output probabilities, each label output probability corresponding to the probability of each phone machine producing a corresponding label. The set of phonetic machines is formed to include a subset of onset phone machines. The stored probabilities of each onset phone macine correspond to at least one phonetic element being uttered at the beginning of a speech segment. The set of phonetic machines is formed to include a subset of trailing phone machines. The stored probabilities of each trailing phone machine correspond to at least one single phonetic element being uttered at the end of a speech segment. Word baseforms are constructed by concatenating phone machines selected from the set.

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

Primary / Asst. Examiners: Harkcom, Gary V.; Knepper, David O.

Maintenance Status: E3 Expired  Check current status

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

       
Related Applications:
Application Number Filed Patent Pub. Date  Title
US1985000738912 1985-05-29       


       
Parent Case:     This is a continuation of application Ser. No. 738,912, filed May 29, 1985, now abandoned.

Family: Show 2 known family members

First Claim:
Show all 19 claims
We claim:     1. In a speech recognition system having an acoustic processor which generates successive labels selected from an alphabet of labels in response to a spoken input wherein the labels are selected based on at least one predefined characteristic and wherein said predefined characteristic varies for at least one given sound depending on whether the sound is located adjacent to a period of silence or not, a method of forming baseforms for words comprising the steps of:
  • forming, for said one given sound, a plurality of different phone machines including a phone machine corresponding to said given sound being uttered adjacent to a period of silence and a phone machine corresponding to said given sound being uttered detached from silence, wherein each phone machine is characterizable as (i) a plurality of states, (ii) a plurality of transitions each of which extends from a state to a state, (iii) means for storing a probability for each transition, and (iv) means for storing label output probabilities, each label output probability corresponding to the probability of said each phone machine producing a particular label at an identified transition;
  • the probabilities for a given phone machine being determined from utterances of a sound corresponding thereto.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 38 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (38)   |   Backward references (6)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 5pp US3588356  1971-06 Moshier et al.   VOCAL PULSE DETECTOR
Get PDF - 17pp US3946157  1976-03 Dreyfus   Speech recognition device for controlling a machine
Get PDF - 27pp US4156868  1979-05 Levinson  Bell Telephone Laboratories, Incorporated Syntactic word recognizer
Get PDF - 38pp US4370521  1983-01 Johnston et al.  Bell Telephone Laboratories, Incorporated Endpoint detector
Get PDF - 27pp US4481593  1984-11 Bahler  Exxon Corporation Continuous speech recognition
Get PDF - 20pp US4587670  1986-05 Levinson et al.  AT&T Bell Laboratories Hidden Markov model speech recognition arrangement
       
Foreign References: None

Other Abstract Info: DERABS G89-300805

Other References:
  • Frederick Jelinek, "Continuous Speech Recognition by Statistical Methods", Proceedings of the IEEE, vol. 64, No. 4, Apr. 1976.
  • H. Bourlard et al, "Speaker Dependent Connected Speech Recognition via Phonemic Markov Models", ICASSP 85 Proceedings, Mar. 1985.
  • R. Bakis, "Spoken Word Spotting Via Centisecond Acoustic States", IBM Technical Disclosure Bulletin, vol. 18, No. 10, Mar. 1976.
  • L. R. Bahl 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
  • L. R. Bahl et al, "Speech Recognition of a Natural Text Read as Isolated Word", IEEE International Conference on Acoustics, Speech and Signal Processing, Atlanta, Ga., U.S., vol. 3, pp. 1168-1171, Apr. 1981.
  • L. R. Bahl, F. Jelinek, R. L. Mercer-"Faster Acoustic Match Computation", Sep. 1980, pp. 1718-1719.
  • L. R. Bahl, F. Jelinek, R. L. Mercer-"A Maximum Likelihood Approach To Continuous Speech Recognition", Mar., 1983, pp. 179-190. (12 pages) Cited by 42 patents


  • 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