Knowledge source personalization to improve language models

Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mappi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Heck, Larry P, Akbacak, Murat, Dumoulin, Benoit, Hakkani-Tur, Dilek Z, Tur, Gokhan
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Heck, Larry P
Akbacak, Murat
Dumoulin, Benoit
Hakkani-Tur, Dilek Z
Tur, Gokhan
description Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US9997157B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US9997157B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US9997157B23</originalsourceid><addsrcrecordid>eNrjZLD2zssvz0lNSU9VKM4vLUpOVShILSrOz0vMyaxKLMnMz1MoyVfIzC0oyi9LVchJzEsvTQQqzc1PSc0p5mFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8aHBlpaW5oam5k5GxkQoAQC0XjAS</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Knowledge source personalization to improve language models</title><source>esp@cenet</source><creator>Heck, Larry P ; Akbacak, Murat ; Dumoulin, Benoit ; Hakkani-Tur, Dilek Z ; Tur, Gokhan</creator><creatorcontrib>Heck, Larry P ; Akbacak, Murat ; Dumoulin, Benoit ; Hakkani-Tur, Dilek Z ; Tur, Gokhan</creatorcontrib><description>Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.</description><language>eng</language><subject>ACOUSTICS ; CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2018</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20180612&amp;DB=EPODOC&amp;CC=US&amp;NR=9997157B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20180612&amp;DB=EPODOC&amp;CC=US&amp;NR=9997157B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Heck, Larry P</creatorcontrib><creatorcontrib>Akbacak, Murat</creatorcontrib><creatorcontrib>Dumoulin, Benoit</creatorcontrib><creatorcontrib>Hakkani-Tur, Dilek Z</creatorcontrib><creatorcontrib>Tur, Gokhan</creatorcontrib><title>Knowledge source personalization to improve language models</title><description>Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.</description><subject>ACOUSTICS</subject><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>MUSICAL INSTRUMENTS</subject><subject>PHYSICS</subject><subject>SPEECH ANALYSIS OR SYNTHESIS</subject><subject>SPEECH OR AUDIO CODING OR DECODING</subject><subject>SPEECH OR VOICE PROCESSING</subject><subject>SPEECH RECOGNITION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2018</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLD2zssvz0lNSU9VKM4vLUpOVShILSrOz0vMyaxKLMnMz1MoyVfIzC0oyi9LVchJzEsvTQQqzc1PSc0p5mFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8aHBlpaW5oam5k5GxkQoAQC0XjAS</recordid><startdate>20180612</startdate><enddate>20180612</enddate><creator>Heck, Larry P</creator><creator>Akbacak, Murat</creator><creator>Dumoulin, Benoit</creator><creator>Hakkani-Tur, Dilek Z</creator><creator>Tur, Gokhan</creator><scope>EVB</scope></search><sort><creationdate>20180612</creationdate><title>Knowledge source personalization to improve language models</title><author>Heck, Larry P ; Akbacak, Murat ; Dumoulin, Benoit ; Hakkani-Tur, Dilek Z ; Tur, Gokhan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US9997157B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2018</creationdate><topic>ACOUSTICS</topic><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>MUSICAL INSTRUMENTS</topic><topic>PHYSICS</topic><topic>SPEECH ANALYSIS OR SYNTHESIS</topic><topic>SPEECH OR AUDIO CODING OR DECODING</topic><topic>SPEECH OR VOICE PROCESSING</topic><topic>SPEECH RECOGNITION</topic><toplevel>online_resources</toplevel><creatorcontrib>Heck, Larry P</creatorcontrib><creatorcontrib>Akbacak, Murat</creatorcontrib><creatorcontrib>Dumoulin, Benoit</creatorcontrib><creatorcontrib>Hakkani-Tur, Dilek Z</creatorcontrib><creatorcontrib>Tur, Gokhan</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Heck, Larry P</au><au>Akbacak, Murat</au><au>Dumoulin, Benoit</au><au>Hakkani-Tur, Dilek Z</au><au>Tur, Gokhan</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Knowledge source personalization to improve language models</title><date>2018-06-12</date><risdate>2018</risdate><abstract>Systems and methods are provided for improving language models for speech recognition by personalizing knowledge sources utilized by the language models to specific users or user-population characteristics. A knowledge source, such as a knowledge graph, is personalized for a particular user by mapping entities or user actions from usage history for the user, such as query logs, to the knowledge source. The personalized knowledge source may be used to build a personal language model by training a language model with queries corresponding to entities or entity pairs that appear in usage history. In some embodiments, a personalized knowledge source for a specific user can be extended based on personalized knowledge sources of similar users.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US9997157B2
source esp@cenet
subjects ACOUSTICS
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
title Knowledge source personalization to improve language models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T10%3A50%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Heck,%20Larry%20P&rft.date=2018-06-12&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS9997157B2%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true