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

 The Delphion Integrated View

  Buy Now:   Buy PDF- 30pp  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: US4817156: Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker
[ Derwent Title ]

Country: US United States of America

View Images High


30 pages

Inventor: Bahl, Lalit R.; Amawalk, NY
Mercer, Robert L.; Yorktown Heights, NY
Nahamoo, David; 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: 1989-03-28 / 1987-08-10

Application Number: US1987000084712

IPC Code: Advanced: G10L 11/00; G10L 15/06; G10L 15/14;
IPC-7: G01L 5/00;

ECLA Code: G10L15/14; T05K999/99;

U.S. Class: Current: 704/256.2; 704/244;
Original: 381/043; 364/513.5;

Field of Search: 381/029-53 364/513,513.5

Priority Number:
1987-08-10  US1987000084712

Abstract:     Apparatus and method for training the statistics of a Markov Model speech recognizer to a subsequent speaker who utters part of a training text after the recognizer has been trained for the statistics of a reference speaker who utters a full training text. Where labels generated by an acoustic processor in response to uttered speech serve as outputs for Markov models, the present apparatus and method determine label output probabilities at transitions in the Markov models corresponding to the subsequent speaker where there is sparse training data. Specifically, label output probabilities for the subsequent speaker are re-parameterized based on confusion matrix entries having values indicative of the similarity between an l th label output of the subsequent speaker and a kth label output for the reference speaker. The label output probabilities based on re-parameterized data are combined with initialized label output probabilities to form "smoothed" label output probabilities which feature smoothed probability distributions. Based on label outputs generated when the subsequent speaker utters the shortened training text, "basic" label output probabilities computed by conventional methodology are linearly averaged against the smoothed label output probabilities to produce improved label output probabilities.

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

Primary / Asst. Examiners: Salce, Patrick R.; Voeltz, Emanuel Todd

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

Designated Country: DE FR GB IT 

Family: Show 10 known family members

First Claim:
Show all 25 claims
We claim:     1. In a speech recognizer in which each successive interval of speech is associated with one label output of an alphabet of label outputs and in which words correspond to respective sequences of Markov model phone machines, wherein each phone machine has a plurality of transitions each extending from a state i to a state j and wherein the probability of each transition and the probability of label outputs being produced at transitions differ among speakers, computerized apparatus for training the recognizer to the probabilities of a subsequent speaker after the recognizer is trained with the probabilities of a reference speaker in response to the utterance by said reference speaker of a sample text, the apparatus comprising:
  • acoustic processor means for outputting a string of one label after another at successive time intervals in response to a speech input;
  • means for computing basic label output probability values from labels generated by said acoustic processor means in response to the subsequent speaker uttering part of the sample text;
  • means for generating smoothed label output probabilities for the subsequent speaker which are based on a similarity measure determined between the subsequent speaker and the reference speaker, the smoothed label output probabilities being more informative than the basic label output probabilities; and
  • means for linear averaging the basic label output probabilities against the smoothed label output probabilities, given the label outputs generated in response to the subsequent speaker uttering said part of the sample text, to produce final label output probabilities.

Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 56 U.S. patent(s) that reference this one

U.S. References: Go to Result Set: All U.S. references   |  Forward references (56)   |   Backward references (9)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 20pp US4587670  1986-05 Levinson et al.  AT&T Bell Laboratories Hidden Markov model speech recognition arrangement
Get PDF - 17pp US4713777  1987-12 Klovstad et al.  Exxon Research and Engineering Company Speech recognition method having noise immunity
Get PDF - 17pp US4713778  1987-12 Baker  Exxon Research and Engineering Company Speech recognition method
Get PDF - 17pp US4718092  1988-01 Klovstad  Exxon Research and Engineering Company Speech recognition activation and deactivation method
Get PDF - 19pp US4718093  1988-01 Brown  Exxon Research and Engineering Company Speech recognition method including biased principal components
Get PDF - 79pp US4718094  1988-01 Bahl et al.  International Business Machines Corp. Speech recognition system
Get PDF - 13pp US4741036  1988-04 Bahl et al.  International Business Machines Corporation Determination of phone weights for markov models in a speech recognition system
Get PDF - 54pp US4748670  1988-05 Bahl et al.  International Business Machines Corporation Apparatus and method for determining a likely word sequence from labels generated by an acoustic processor
Get PDF - 35pp US4759068  1988-07 Bahl et al.  International Business Machines Corporation Constructing Markov models of words from multiple utterances
Foreign References: None

Other References:
  • "An Introduction to Hidden Markov Models", Rabiner et al., IEEE ASSP Magazine, Jan. 1986, pp. 4-7.

  • 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