Method and apparatus for detecting spoofing conditions

An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features acc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nagarsheth, Parav, Khoury, Elie, Patil, Kailash, Garland, Matthew
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 Nagarsheth, Parav
Khoury, Elie
Patil, Kailash
Garland, Matthew
description An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US10692502B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US10692502B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US10692502B23</originalsourceid><addsrcrecordid>eNrjZDDzTS3JyE9RSMwD4oKCxKLEktJihbT8IoWU1JLU5JLMvHSF4oL8_DQQIzk_LyWzJDM_r5iHgTUtMac4lRdKczMourmGOHvophbkx6cWFyQmp-allsSHBhsamFkamRoYORkZE6MGAL23LgU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method and apparatus for detecting spoofing conditions</title><source>esp@cenet</source><creator>Nagarsheth, Parav ; Khoury, Elie ; Patil, Kailash ; Garland, Matthew</creator><creatorcontrib>Nagarsheth, Parav ; Khoury, Elie ; Patil, Kailash ; Garland, Matthew</creatorcontrib><description>An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.</description><language>eng</language><subject>ACOUSTICS ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2020</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=20200623&amp;DB=EPODOC&amp;CC=US&amp;NR=10692502B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20200623&amp;DB=EPODOC&amp;CC=US&amp;NR=10692502B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Nagarsheth, Parav</creatorcontrib><creatorcontrib>Khoury, Elie</creatorcontrib><creatorcontrib>Patil, Kailash</creatorcontrib><creatorcontrib>Garland, Matthew</creatorcontrib><title>Method and apparatus for detecting spoofing conditions</title><description>An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.</description><subject>ACOUSTICS</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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDDzTS3JyE9RSMwD4oKCxKLEktJihbT8IoWU1JLU5JLMvHSF4oL8_DQQIzk_LyWzJDM_r5iHgTUtMac4lRdKczMourmGOHvophbkx6cWFyQmp-allsSHBhsamFkamRoYORkZE6MGAL23LgU</recordid><startdate>20200623</startdate><enddate>20200623</enddate><creator>Nagarsheth, Parav</creator><creator>Khoury, Elie</creator><creator>Patil, Kailash</creator><creator>Garland, Matthew</creator><scope>EVB</scope></search><sort><creationdate>20200623</creationdate><title>Method and apparatus for detecting spoofing conditions</title><author>Nagarsheth, Parav ; Khoury, Elie ; Patil, Kailash ; Garland, Matthew</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US10692502B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</creationdate><topic>ACOUSTICS</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>Nagarsheth, Parav</creatorcontrib><creatorcontrib>Khoury, Elie</creatorcontrib><creatorcontrib>Patil, Kailash</creatorcontrib><creatorcontrib>Garland, Matthew</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Nagarsheth, Parav</au><au>Khoury, Elie</au><au>Patil, Kailash</au><au>Garland, Matthew</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method and apparatus for detecting spoofing conditions</title><date>2020-06-23</date><risdate>2020</risdate><abstract>An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US10692502B2
source esp@cenet
subjects ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
title Method and apparatus for detecting spoofing conditions
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T18%3A00%3A08IST&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=Nagarsheth,%20Parav&rft.date=2020-06-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS10692502B2%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