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: US6067517: Transcription of speech data with segments from acoustically dissimilar environments
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
12 pages

 
Inventor: Bahl, Lalit Rai; Amawalk, NY
Gopalakrishnan, Ponani; Yorktown Heights, NY
Gopinath, Ramesh Ambat; White Plains, NY
Maes, Stephane Herman; Danbury, CT
Panmanabhan, Mukund; Ossining, NY
Polymenakos, Lazaros; 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: 2000-05-23 / 1996-02-02

Application Number: US1996000595722

IPC Code: Advanced: G10L 15/20;
IPC-7: G10L 15/20;

ECLA Code: G10L15/20; S10L15/20;

U.S. Class: Current: 704/256.4; 704/242; 704/E15.039;
Original: 704/256; 704/242;

Field of Search: 395/2.44,2.52,2.53,2.86,2.4,2.79,2.6,2.64 704/235,236,243,244,245,251,252,255,256,257,277,276,270,278,200,242,241

Government Interest:     The invention was developed under US Government Contract number 33690098 "Robust Context Dependent Models and Features for Continuous Speech Recognition". The US Government has certain rights to the invention.

Priority Number:
1996-02-02  US1996000595722

Abstract:     A technique to improve the recognition accuracy when transcribing speech data that contains data from a wide range of environments. Input data in many situations contains data from a variety of sources in different environments. Such classes include: clean speech, speech corrupted by noise (e.g., music), non-speech (e.g., pure music with no speech), telephone speech, and the identity of a speaker. A technique is described whereby the different classes of data are first automatically identified, and then each class is transcribed by a system that is made specifically for it. The invention also describes a segmentation algorithm that is based on making up an acoustic model that characterizes the data in each class, and then using a dynamic programming algorithm (the viterbi algorithm) to automatically identify segments that belong to each class. The acoustic models are made in a certain feature space, and the invention also describes different feature spaces for use with different classes.

Attorney, Agent or Firm: Ryan & Mason, L.L.P. ; Otterstedt, Paul J. ;

Primary / Asst. Examiners: Dorvil, Richemond;

Maintenance Status: CC Certificate of Correction issued

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

Designated Country: DE GB 

Family: Show 6 known family members

First Claim:
Show all 37 claims
What is claimed is:     1. A method for transcribing a segment of data that includes speech in one or more environments and non-speech data, comprising:
  • inputting the data to a segmenter and producing a series of segments, each segment being given a type identifier tag selected from a predetermined set of classes; and
  • transcribing each type identifier tagged segment using a specific system created for that type.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 54 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (54)   |   Backward references (3)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 24pp US4430726  1984-02 Kasday  Bell Telephone Laboratories, Incorporated Dictation/transcription method and arrangement
Get PDF - 14pp US5333275  1994-07 Wheatley et al.   System and method for time aligning speech
Get PDF - 19pp US5579436  1996-11 Chou et al.  Lucent Technologies Inc. Recognition unit model training based on competing word and word string models
       
Foreign References:
Buy
PDF
Publication Date IPC Code Assignee   Title
Get PDF - 37pp EP0645757A1 1995-03  G10L 7/08 XEROX CORP Semantic co-occurrence filtering for speech recognition and signal transcription applications 
Get PDF - 15pp EP0649144A1 1995-04  G11B 27/28 IBM Automatic indexing of audio using speech recognition 
Get PDF - 34pp WO9528700 1995-10  G10L 9/00 BOLT BERANEK & NEWMAN TOPIC DISCRIMINATOR 


Other Abstract Info: DERABS G1997-387716

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