Adaptive confidence thresholds for speech recognition

Adaptive confidence thresholds for speech recognition

Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirma...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Stubley, Peter, Monzon, Oded, Gorodetski, Alex, Peters, Douglas
Format: Patent
Sprache:eng
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 Stubley, Peter
Monzon, Oded
Gorodetski, Alex
Peters, Douglas
description Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.
format Patent
fullrecord <record><control><sourceid>uspatents_EFH</sourceid><recordid>TN_cdi_uspatents_grants_08239203</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>08239203</sourcerecordid><originalsourceid>FETCH-uspatents_grants_082392033</originalsourceid><addsrcrecordid>eNrjZDB1TEksKMksS1VIzs9Ly0xJzUtOVSjJKEotzsjPSSlWSMsvUiguSE1NzlAoSk3OT8_LLMnMz-NhYE1LzClO5YXS3AwKbq4hzh66pcUFiSWpeSXF8elFiSDKwMLI2NLIwNiYCCUAZzkufA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Adaptive confidence thresholds for speech recognition</title><source>USPTO Issued Patents</source><creator>Stubley, Peter ; Monzon, Oded ; Gorodetski, Alex ; Peters, Douglas</creator><creatorcontrib>Stubley, Peter ; Monzon, Oded ; Gorodetski, Alex ; Peters, Douglas ; Nuance Communications, Inc</creatorcontrib><description>Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.</description><language>eng</language><creationdate>2012</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/8239203$$EPDF$$P50$$Guspatents$$Hfree_for_read</linktopdf><link.rule.ids>230,308,780,802,885,64038</link.rule.ids><linktorsrc>$$Uhttps://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/8239203$$EView_record_in_USPTO$$FView_record_in_$$GUSPTO$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Stubley, Peter</creatorcontrib><creatorcontrib>Monzon, Oded</creatorcontrib><creatorcontrib>Gorodetski, Alex</creatorcontrib><creatorcontrib>Peters, Douglas</creatorcontrib><creatorcontrib>Nuance Communications, Inc</creatorcontrib><title>Adaptive confidence thresholds for speech recognition</title><description>Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.</description><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2012</creationdate><recordtype>patent</recordtype><sourceid>EFH</sourceid><recordid>eNrjZDB1TEksKMksS1VIzs9Ly0xJzUtOVSjJKEotzsjPSSlWSMsvUiguSE1NzlAoSk3OT8_LLMnMz-NhYE1LzClO5YXS3AwKbq4hzh66pcUFiSWpeSXF8elFiSDKwMLI2NLIwNiYCCUAZzkufA</recordid><startdate>20120807</startdate><enddate>20120807</enddate><creator>Stubley, Peter</creator><creator>Monzon, Oded</creator><creator>Gorodetski, Alex</creator><creator>Peters, Douglas</creator><scope>EFH</scope></search><sort><creationdate>20120807</creationdate><title>Adaptive confidence thresholds for speech recognition</title><author>Stubley, Peter ; Monzon, Oded ; Gorodetski, Alex ; Peters, Douglas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-uspatents_grants_082392033</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2012</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Stubley, Peter</creatorcontrib><creatorcontrib>Monzon, Oded</creatorcontrib><creatorcontrib>Gorodetski, Alex</creatorcontrib><creatorcontrib>Peters, Douglas</creatorcontrib><creatorcontrib>Nuance Communications, Inc</creatorcontrib><collection>USPTO Issued Patents</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Stubley, Peter</au><au>Monzon, Oded</au><au>Gorodetski, Alex</au><au>Peters, Douglas</au><aucorp>Nuance Communications, Inc</aucorp><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Adaptive confidence thresholds for speech recognition</title><date>2012-08-07</date><risdate>2012</risdate><abstract>Adjusting confidence score thresholds is described for a speech recognition engine. The speech recognition engine is implemented in multiple computer processes functioning in a computer processor, and is characterized by an associated receiver operating characteristic (ROC) curve. A results confirmation process interprets user confirmation of speech recognition results within a given confidence score threshold to create a confirmed portion of the ROC curve for the speech recognition engine. A curve extension process extends the confirmed portion of the ROC curve by extrapolation of unconfirmed speech recognition results beyond the confidence score threshold to generate an extended ROC curve. A threshold adjustment process adjusts the confidence score threshold based on the extended ROC curve to meet target operating constraints for operating the speech recognition engine to perform automatic speech recognition of user speech inputs.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_uspatents_grants_08239203
source USPTO Issued Patents
title Adaptive confidence thresholds for speech recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T03%3A19%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-uspatents_EFH&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Stubley,%20Peter&rft.aucorp=Nuance%20Communications,%20Inc&rft.date=2012-08-07&rft_id=info:doi/&rft_dat=%3Cuspatents_EFH%3E08239203%3C/uspatents_EFH%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