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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 12pp  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: US4817158: Normalization of speech signals
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
12 pages

 
Inventor: 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: 1989-03-28 / 1984-10-19

Application Number: US1984000662867

IPC Code: Advanced: G10L 11/00; G10L 15/00; G10L 15/02; G10L 15/20; G10L 21/02;
Core: G10L 21/00; more...
IPC-7: G10L 5/00;

U.S. Class: Current: 704/224; 704/E15.004;
Original: 381/047; 381/043;

Field of Search: 381/036-43,46-52,94 382/018

Priority Number:
1984-10-19  US1984000662867

Abstract: A method and a system are disclosed for normalizing a speech signal prior to a speech recognition process. In a preparatory procedure, a sample interval of speech is separated into thirty-one frequency bands and an amplitude histogram is generated for each band. From these histograms, the 5% percentile amplitude value P(05) and the 95% percentile amplitude value P(95) are extracted for each band and these values are stored for later reference. For actual normalization, the current speech signal is also divided into the same frequency band as in the preparatory procedure, and consecutive input amplitude values A(in) of each frequency band are modified, using the percentile values of the respective band, to obtain output values according to [Figure] The essential effect of this normalizing treatment is that the resulting long-term spectrum is given by the P(95) values and the spectrum of silence is given by the P(05) values. After normalization, all speech has the same silence spectrum and long-term spectrum.

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

Primary / Asst. Examiners: Kemeny, Emanuel S.; Knepper, David D.

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

Designated Country: DE FR GB IT 

Family: Show 6 known family members

First Claim:
Show all 10 claims
What I claim is:     1. A method for overcoming the distortions in the spectrum-of-silence in a system for accepting words presented in a stream of continuous speech, processing the stream into amplitude histograms for respective frequencies, and carrying out recognition processes, characterized by
  • (a) collecting amplitude histograms as a function of frequency;
  • (b) extracting, for each frequency, the amplitude P(05) defining the 5th percentile and the amplitude P(95) defining the 95th percentile; and
  • (c) normalizing, for each frequency, the input amplitude A(in) of the speech signal to obtain an output signal amplitude [Figure]


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 17 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (17)   |   Backward references (12)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 37pp USRE32172  1986-06 Johnston et al.  AT&T Bell Laboratories Endpoint detector
Get PDF - 11pp US2938079  1960-05 Flanagan   Spectrum segmentation system for the automatic extraction of formant frequencies from human speech
Get PDF - 13pp US4038503  1977-07 Moshier  Dialog Systems, Inc. Speech recognition apparatus
Get PDF - 6pp US4060694  1977-11 Suzuki et al.  Fuji Xerox Co., Ltd. Speech recognition method and apparatus adapted to a plurality of different speakers
Get PDF - 13pp US4069393  1978-01 Martin et al.  Threshold Technology, Inc. Word recognition apparatus and method
Get PDF - 17pp US4087630  1978-05 Browning et al.  Centigram Corporation Continuous speech recognition apparatus
Get PDF - 41pp US4184049  1979-01 Crochiere et al.  Bell Telephone Laboratories, Incorporated Transform speech signal coding with pitch controlled adaptive quantizing
Get PDF - 20pp US4286115  1981-08 Sakoe  Nippon Electric Co., Ltd. System for recognizing words continuously spoken according to a format
Get PDF - 13pp US4315319  1982-02 White  Rockwell International Corporation Non-linear signal processor
Get PDF - 18pp US4388495  1983-06 Hitchcock  Interstate Electronics Corporation Speech recognition microcomputer
Get PDF - 9pp US4426551  1984-01 Komatsu et al.  Hitachi, Ltd. Speech recognition method and device
Get PDF - 31pp US4567610  1986-01 McConnell  Wayland Research Inc. Method of and apparatus for pattern recognition
       
Foreign References: None

Other Abstract Info: DERABS G86-145297

Other References:
  • P. S. Cohen et al., "Automatic Amplitude Normalization of Speech", IBM Technical Disclosure Bulletin, vol. 16, No. 8, pp. 2610-2611, New York, U.S.A., Jan. 1974.
  • S. K. Das, "Amplitude Normalization for Discrete Utterance Recogntion", IBM Technical Disclosure Bulletin, vol. 22, No. 12, pp. 5524-5525, New York, U.S.A., May 1980.
  • H. F. Silverman et al., "A Parametrically Controlled Spectral Analysis System for Speech", IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-22, No. 5, pp. 362-381, Oct. 1974. (20 pages) Cited by 3 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