System and method of word lattice augmentation using a pre/post vocalic consonant distinction

Systems and methods are provided for recognizing speech in a spoken dialogue system. The method includes receiving input speech having a pre-vocalic consonant or a post-vocalic consonant, generating at least one output lattice that calculates a first score by comparing the input speech to a training...

Full description

Saved in:
Bibliographic Details
Main Authors Kim, Yeon-Jun, Conkie, Alistair, Ljolje, Andrej, Syrdal, Ann K
Format Patent
LanguageEnglish
Published 20.09.2011
Online AccessGet full text

Cover

Abstract Systems and methods are provided for recognizing speech in a spoken dialogue system. The method includes receiving input speech having a pre-vocalic consonant or a post-vocalic consonant, generating at least one output lattice that calculates a first score by comparing the input speech to a training model to provide a result and distinguishing between the pre-vocalic consonant and the post-vocalic consonant in the input speech. A second score is calculated by measuring a similarity between the pre-vocalic consonant or the post vocalic consonant in the input speech and the first score. At least one category is determined for the pre-vocalic match or mismatch or the post-vocalic match or mismatch by using the second score and the results of the an automated speech recognition (ASR) system are refined by using the at least one category for the pre-vocalic match or mismatch or the post-vocalic match or mismatch.
AbstractList Systems and methods are provided for recognizing speech in a spoken dialogue system. The method includes receiving input speech having a pre-vocalic consonant or a post-vocalic consonant, generating at least one output lattice that calculates a first score by comparing the input speech to a training model to provide a result and distinguishing between the pre-vocalic consonant and the post-vocalic consonant in the input speech. A second score is calculated by measuring a similarity between the pre-vocalic consonant or the post vocalic consonant in the input speech and the first score. At least one category is determined for the pre-vocalic match or mismatch or the post-vocalic match or mismatch by using the second score and the results of the an automated speech recognition (ASR) system are refined by using the at least one category for the pre-vocalic match or mismatch or the post-vocalic match or mismatch.
Author Kim, Yeon-Jun
Ljolje, Andrej
Conkie, Alistair
Syrdal, Ann K
Author_xml – sequence: 1
  givenname: Yeon-Jun
  surname: Kim
  fullname: Kim, Yeon-Jun
– sequence: 2
  givenname: Alistair
  surname: Conkie
  fullname: Conkie, Alistair
– sequence: 3
  givenname: Andrej
  surname: Ljolje
  fullname: Ljolje, Andrej
– sequence: 4
  givenname: Ann K
  surname: Syrdal
  fullname: Syrdal, Ann K
BookMark eNqNzD0OwjAMQOEMMPB3B18A0QIDzAjEDitCVuKWSKldxQ6I20MlDsD0lk9v6kYsTBN3u7zVqAPkAB3ZQwJIAy_JARKaRU-Ape2IDS0KQ9HILSD0mVa9qMFTPKbowQurMLJBiGqR_cDnbtxgUlr8OnNwOl4P52XRHu071XubcUi1q9bbel9v_iAfD7E_PQ
ContentType Patent
CorporateAuthor AT&T Intellectual Property II, L.P
CorporateAuthor_xml – name: AT&T Intellectual Property II, L.P
DBID EFH
DatabaseName USPTO Issued Patents
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EFH
  name: USPTO Issued Patents
  url: http://www.uspto.gov/patft/index.html
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 08024191
GroupedDBID EFH
ID FETCH-uspatents_grants_080241913
IEDL.DBID EFH
IngestDate Sun Mar 05 22:32:09 EST 2023
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-uspatents_grants_080241913
OpenAccessLink https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/8024191
ParticipantIDs uspatents_grants_08024191
PatentNumber 8024191
PublicationCentury 2000
PublicationDate 20110920
PublicationDateYYYYMMDD 2011-09-20
PublicationDate_xml – month: 09
  year: 2011
  text: 20110920
  day: 20
PublicationDecade 2010
PublicationYear 2011
References Nitta (5133012) 19920700
Hunt (7146319) 20061200
Yaman et al. (7856351) 20101200
Charlesworth et al. (7337116) 20080200
Guan et al. (6502073) 20021200
Komissarchik et al. (5799276) 19980800
References_xml – year: 19920700
  ident: 5133012
  contributor:
    fullname: Nitta
– year: 19980800
  ident: 5799276
  contributor:
    fullname: Komissarchik et al.
– year: 20061200
  ident: 7146319
  contributor:
    fullname: Hunt
– year: 20101200
  ident: 7856351
  contributor:
    fullname: Yaman et al.
– year: 20021200
  ident: 6502073
  contributor:
    fullname: Guan et al.
– year: 20080200
  ident: 7337116
  contributor:
    fullname: Charlesworth et al.
Score 2.81279
Snippet Systems and methods are provided for recognizing speech in a spoken dialogue system. The method includes receiving input speech having a pre-vocalic consonant...
SourceID uspatents
SourceType Open Access Repository
Title System and method of word lattice augmentation using a pre/post vocalic consonant distinction
URI https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/8024191
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5qEdSTomJ9MQeva1NNYnKWhiAoPSj0ImWzjyC0m9Bs7N93JinFi153YRhmd3Zmlu-bAbijK_BkkjgWcmILEWqbikRZK0zCY7iLojABs5Ff3-L8I3yZR_MB5DsuzIrcSNSkS3PfNrWvOnAlPe_9wYu--TP3CHTcfWDjlpXUM23HCQWbCdPY95KAoV3TLD-CAxJBKZvzza-gkR3D_qxbPYGBcafw2TcHRyrdsZ_bjJXFDRV_uJSeMWgo23K15QI5ZER6iRLrtRnXVePxm8POl0KqYDl_dh41O6jrmAlngNn0_TkXO10W5ZoxLotgq_PjOQyp1jcXgCqUD1LHhvxQhUpHaaojpVNjI0VG1cEIRn-Kufxn7woO-8_QlNziGoZ-3Zobiqa-uO1M9QNLY4OC
link.rule.ids 230,309,786,808,891,64396
linkProvider USPTO
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8MwDLamgXicQIAYTx-4hm3QlvYMVOU17QDSLmhK85iQtrRaM_b3sdtp4gLXRLIsJ85nR_5sgCu6AncmjiIh-zYXgbaJiJW1wsQ8hjvPc9NjNvLbIMo-gudROGpBtubCzMiNREm6VNeLqvRFXVxJz3tz8KJp_sw9Ah13H1i6aSH1UNtuTGDTZxr7BmMs3_XHNNuFbRJCQZvz1S_YSPdgc1iv7kPLuAP4bNqDIyXv2ExuxsLiktI_nErPVWgoF5PZig3kkGvSJyixnJtuWVQevxl4vhRSDssRtPOo2UVdzU04BEwf3-8zsdZlPJlzlcu4t9L69gjalO2bY0AVyBupI0OeqAKlwyTRodKJsaEis-peBzp_ijn5Z-8StoYP6fj1afByCjvNz2hCPnIGbT9fmHOCVp9f1Fb7AeQHhn4
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=System+and+method+of+word+lattice+augmentation+using+a+pre%2Fpost+vocalic+consonant+distinction&rft.inventor=Kim%2C+Yeon-Jun&rft.inventor=Conkie%2C+Alistair&rft.inventor=Ljolje%2C+Andrej&rft.inventor=Syrdal%2C+Ann+K&rft.number=8024191&rft.date=2011-09-20&rft.externalDBID=n%2Fa&rft.externalDocID=08024191