Neural network method and apparatus

A method and apparatus for training a recognition model and a recognition method and apparatus using the model are disclosed. The apparatus for training the model obtains an estimation hidden vector output from a hidden layer of the model in response to an estimation output vector output from the mo...

Full description

Saved in:
Bibliographic Details
Main Author Na, Hwidong
Format Patent
LanguageEnglish
Published 23.03.2021
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

Abstract A method and apparatus for training a recognition model and a recognition method and apparatus using the model are disclosed. The apparatus for training the model obtains an estimation hidden vector output from a hidden layer of the model in response to an estimation output vector output from the model at a previous time being input into the model at a current time, and trains the model such that the estimation hidden vector of the current time matches an answer hidden vector output from the hidden layer in response to an answer output vector, corresponding to the estimation output vector of the previous time, being input into the model at the current time.
AbstractList A method and apparatus for training a recognition model and a recognition method and apparatus using the model are disclosed. The apparatus for training the model obtains an estimation hidden vector output from a hidden layer of the model in response to an estimation output vector output from the model at a previous time being input into the model at a current time, and trains the model such that the estimation hidden vector of the current time matches an answer hidden vector output from the hidden layer in response to an answer output vector, corresponding to the estimation output vector of the previous time, being input into the model at the current time.
Author Na, Hwidong
Author_xml – fullname: Na, Hwidong
BookMark eNrjYmDJy89L5WRQ9kstLUrMUchLLSnPL8pWyE0tychPUUjMA-KCgsSixJLSYh4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicCtQeHxpsaGBpam5sYOlkZEyMGgDQnSh2
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US10957309B2
GroupedDBID EVB
ID FETCH-epo_espacenet_US10957309B23
IEDL.DBID EVB
IngestDate Fri Jul 19 14:48:38 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US10957309B23
Notes Application Number: US201715838519
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210323&DB=EPODOC&CC=US&NR=10957309B2
ParticipantIDs epo_espacenet_US10957309B2
PublicationCentury 2000
PublicationDate 20210323
PublicationDateYYYYMMDD 2021-03-23
PublicationDate_xml – month: 03
  year: 2021
  text: 20210323
  day: 23
PublicationDecade 2020
PublicationYear 2021
RelatedCompanies SAMSUNG ELECTRONICS CO., LTD
RelatedCompanies_xml – name: SAMSUNG ELECTRONICS CO., LTD
Score 3.3117752
Snippet A method and apparatus for training a recognition model and a recognition method and apparatus using the model are disclosed. The apparatus for training the...
SourceID epo
SourceType Open Access Repository
SubjectTerms ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Title Neural network method and apparatus
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210323&DB=EPODOC&locale=&CC=US&NR=10957309B2
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMTZJTDKySDbUTUpONNM1SUsx0U0E1qPArophErB6SrY0TAQN6Pv6mXmEmnhFmEYwMWTB9sKAzwktBx-OCMxRycD8XgIurwsQg1gu4LWVxfpJmUChfHu3EFsXNWjv2Ah0PJyxmouTrWuAv4u_s5qzs21osJpfELCta2kKTMyWTsDimhXUjAads-8a5gTalVKAXKW4CTKwBQBNyysRYmBKzRNm4HSG3bwmzMDhC53wFmZgB6_QTC4GCkJzYbEIgzLoRI3EHIU8yBJuBcgt0AqJeUBcAD7Lu7RYlEHRzTXE2UMXaG883JPxocEIJxqLMbAAO_-pEgwKFsD2iblForFBmmkyqPFikWaQDLpnMS3JPMki0cRYkkEKtzlS-CSlGbhAAQZaT2VkLMPAUlJUmioLrGBLkuTAIQMA72V98g
link.rule.ids 230,309,786,891,25594,76906
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMTZJTDKySDbUTUpONNM1SUsx0U0E1qPArophErB6SrY0TAQN6Pv6mXmEmnhFmEYwMWTB9sKAzwktBx-OCMxRycD8XgIurwsQg1gu4LWVxfpJmUChfHu3EFsXNWjv2Ah0PJyxmouTrWuAv4u_s5qzs21osJpfELCta2kKTMyWTsDimtUcdDovqOkU5gTalVKAXKW4CTKwBQBNyysRYmBKzRNm4HSG3bwmzMDhC53wFmZgB6_QTC4GCkJzYbEIgzLoRI3EHIU8yBJuBcgt0AqJeUBcAD7Lu7RYlEHRzTXE2UMXaG883JPxocEIJxqLMbAAO_-pEgwKFsD2iblForFBmmkyqPFikWaQDLpnMS3JPMki0cRYkkEKtzlS-CTlGTg9Qnx94n08_bylGbhAgQdaW2VkLMPAUlJUmioLrGxLkuTAoQQA-56A3w
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=Neural+network+method+and+apparatus&rft.inventor=Na%2C+Hwidong&rft.date=2021-03-23&rft.externalDBID=B2&rft.externalDocID=US10957309B2