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

 The Delphion Integrated View

  Buy Now:   Buy PDF- 14pp  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: US5682501: Speech synthesis system
[ Derwent Title ]

Country: US United States of America

View Images High


14 pages

Inventor: Sharman, Richard Anthony; Southampton, United Kingdom

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: 1997-10-28 / 1995-02-21

Application Number: US1995000391731

IPC Code: Advanced: G10L 13/08; G10L 13/04;
IPC-7: G10L 0/00;

ECLA Code: G10L13/08; S10L13/04; S10L13/08;

U.S. Class: Current: 704/260; 704/256; 704/256.4; 704/257; 704/258; 704/261; 704/266; 704/269; 704/E13.011;
Original: 395/002.69; 395/002.75; 395/002.78; 395/002.67;

Field of Search: 381/041,43 395/2.65,2.66,2.75,2.67,2.7

Priority Number:
1994-06-22  GB1994000012555

Abstract:     A speech synthesis unit comprises a text processor which breaks down text into phonemes, a prosodic processor which assigns properties such as length and pitch to the phonemes based on context, and a synthesis unit which outputs an audio signal representing the sequence of phonemes according to the specified properties. The prosodic processor includes a Hidden Markov Model (HMM) to predict the durations of the phonemes. Each state of the HMM represents a duration, and the outputs are phonemes. The HMM is trained on a set of data consisting of phonemes of known identity and duration, to allow the state transition and output distributions to be calculated. The HMM can then be used for any given input sequence of phonemes to predict a most likely sequence of corresponding durations.

Attorney, Agent or Firm: Whitham, Curtis, Whitham & McGinn ; Tassinari, Jr., Robert P. ;

Primary / Asst. Examiners: MacDonald, Allen R.; Opsasnick, Michael

Maintenance Status: E2 Expired  Check current status

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

Designated Country: DE FR GB 

Family: Show 4 known family members

First Claim:
Show all 10 claims
We claim:     1. A method for generating synthesized speech from input text, the method comprising the steps of:
  • decomposing the input text into a sequence of speech units;
  • estimating a duration value for each speech unit in the sequence of speech units;
  • synthesizing speech based on said sequence of speech units and duration values;
  • characterized in that said estimating step utilizes a Hidden Markov Model (HMM) to determine the most likely sequence of duration values given said sequence of speech units, wherein each state of the HMM represents a duration value and each output from the HMM is a speech unit.

Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 36 U.S. patent(s) that reference this one

U.S. References: Go to Result Set: All U.S. references   |  Forward references (36)   |   Backward references (7)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 33pp US4783804  1988-11 Juang et al.  American Telephone and Telegraph Company, AT&T Bell Laboratories Hidden Markov model speech recognition arrangement
Get PDF - 28pp US4852180  1989-07 Levinson  American Telephone and Telegraph Company, AT&T Bell Laboratories Speech recognition by acoustic/phonetic system and technique
Get PDF - 45pp US4980918  1990-12 Bahl et al.  International Business Machines Corporation Speech recognition system with efficient storage and rapid assembly of phonological graphs
Get PDF - 31pp US5033087  1991-07 Bahl et al.  International Business Machines Corp. Method and apparatus for the automatic determination of phonological rules as for a continuous speech recognition system
Get PDF - 12pp US5268990  1993-12 Cohen et al.  SRI International Method for recognizing speech using linguistically-motivated hidden Markov models
Get PDF - 29pp US5390278  1995-02 Gupta et al.  Bell Canada Phoneme based speech recognition
Get PDF - 15pp US5502790  1996-03 Yi  Oki Electric Industry Co., Ltd. Speech recognition method and system using triphones, diphones, and phonemes
Foreign References:
Publication Date IPC Code Assignee   Title
Get PDF - 21pp EP0481107A1 1990-10  G10L 5/04 IBM A phonetic Hidden Markov Model speech synthesizer 
Get PDF - 18pp EP0515709A1 1991-05  G10L 5/04 IBM Method and apparatus for segmental unit representation in text-to-speech synthesis 
Get PDF - 21pp EP0481107A1 1992-04  G01L 3/00 IBM A phonetic Hidden Markov Model speech synthesizer 
Get PDF - 18pp EP0515709A1 1992-12  G10L 5/04 IBM Method and apparatus for segmental unit representation in text-to-speech synthesis 
Get PDF - 14pp EP0588646A2 1993-09  H04M 3/42 BOSTON TECH INC Automatic telephone system 
Get PDF - 14pp EP0588646A2 1994-03  H04M 3/38 BOSTON TECH INC Automatic telephone system 

Other Abstract Info: DERABS G96-032496

Other References:
  • European Search Report dated Oct. 9, 1995.
  • Fundamentals of Speech Recognition, Rabiner and Juang, Prentice Hall, 1993, p. 349.

  • 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