Pre-processing speech for speech recognition

Pre-processing speech for speech recognition

A method for pre-processing speech, in particular for recognizing speech, including receiving a speech signal, separating a spectrum of said speech signal into a number of predetermined frequency sub-bands, analyzing said speech signal within each of said frequency sub-bands, generating respective b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tato, Raquel, Kemp, Thomas, Abella, Antoni
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 Tato, Raquel
Kemp, Thomas
Abella, Antoni
description A method for pre-processing speech, in particular for recognizing speech, including receiving a speech signal, separating a spectrum of said speech signal into a number of predetermined frequency sub-bands, analyzing said speech signal within each of said frequency sub-bands, generating respective band-dependent acoustic feature data for each of said respective frequency sub-bands, deriving band-dependent likelihoods for occurrences of speech elements or within said speech signal based on said band-dependent acoustic feature data, analyzing said speech signal within said spectrum, generating full-band acoustic feature data, which are at least in part representative for said speech signal with respect to said spectrum, deriving a full-band likelihood for occurrences of speech elements or of sequences thereof within said speech signal based on said full-band acoustic feature data, deriving an overall likelihood for occurrences of speech elements within said speech signal based on said band-dependent likelihoods and said full-band likelihood.
format Patent
fullrecord <record><control><sourceid>uspatents_EFH</sourceid><recordid>TN_cdi_uspatents_grants_07376559</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>07376559</sourcerecordid><originalsourceid>FETCH-uspatents_grants_073765593</originalsourceid><addsrcrecordid>eNrjZNAJKErVLSjKT04tLs7MS1coLkhNTc5QSMsvgjGLUpPz0_MySzLz83gYWNMSc4pTeaE0N4OCm2uIs4duaXFBYklqXklxfHpRIogyMDc2NzM1tTQmQgkAg-Qq_g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Pre-processing speech for speech recognition</title><source>USPTO Issued Patents</source><creator>Tato, Raquel ; Kemp, Thomas ; Abella, Antoni</creator><creatorcontrib>Tato, Raquel ; Kemp, Thomas ; Abella, Antoni ; Sony Deutschland GmbH</creatorcontrib><description>A method for pre-processing speech, in particular for recognizing speech, including receiving a speech signal, separating a spectrum of said speech signal into a number of predetermined frequency sub-bands, analyzing said speech signal within each of said frequency sub-bands, generating respective band-dependent acoustic feature data for each of said respective frequency sub-bands, deriving band-dependent likelihoods for occurrences of speech elements or within said speech signal based on said band-dependent acoustic feature data, analyzing said speech signal within said spectrum, generating full-band acoustic feature data, which are at least in part representative for said speech signal with respect to said spectrum, deriving a full-band likelihood for occurrences of speech elements or of sequences thereof within said speech signal based on said full-band acoustic feature data, deriving an overall likelihood for occurrences of speech elements within said speech signal based on said band-dependent likelihoods and said full-band likelihood.</description><language>eng</language><creationdate>2008</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/7376559$$EPDF$$P50$$Guspatents$$Hfree_for_read</linktopdf><link.rule.ids>230,308,780,802,885,64039</link.rule.ids><linktorsrc>$$Uhttps://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/7376559$$EView_record_in_USPTO$$FView_record_in_$$GUSPTO$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Tato, Raquel</creatorcontrib><creatorcontrib>Kemp, Thomas</creatorcontrib><creatorcontrib>Abella, Antoni</creatorcontrib><creatorcontrib>Sony Deutschland GmbH</creatorcontrib><title>Pre-processing speech for speech recognition</title><description>A method for pre-processing speech, in particular for recognizing speech, including receiving a speech signal, separating a spectrum of said speech signal into a number of predetermined frequency sub-bands, analyzing said speech signal within each of said frequency sub-bands, generating respective band-dependent acoustic feature data for each of said respective frequency sub-bands, deriving band-dependent likelihoods for occurrences of speech elements or within said speech signal based on said band-dependent acoustic feature data, analyzing said speech signal within said spectrum, generating full-band acoustic feature data, which are at least in part representative for said speech signal with respect to said spectrum, deriving a full-band likelihood for occurrences of speech elements or of sequences thereof within said speech signal based on said full-band acoustic feature data, deriving an overall likelihood for occurrences of speech elements within said speech signal based on said band-dependent likelihoods and said full-band likelihood.</description><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2008</creationdate><recordtype>patent</recordtype><sourceid>EFH</sourceid><recordid>eNrjZNAJKErVLSjKT04tLs7MS1coLkhNTc5QSMsvgjGLUpPz0_MySzLz83gYWNMSc4pTeaE0N4OCm2uIs4duaXFBYklqXklxfHpRIogyMDc2NzM1tTQmQgkAg-Qq_g</recordid><startdate>20080520</startdate><enddate>20080520</enddate><creator>Tato, Raquel</creator><creator>Kemp, Thomas</creator><creator>Abella, Antoni</creator><scope>EFH</scope></search><sort><creationdate>20080520</creationdate><title>Pre-processing speech for speech recognition</title><author>Tato, Raquel ; Kemp, Thomas ; Abella, Antoni</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-uspatents_grants_073765593</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2008</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Tato, Raquel</creatorcontrib><creatorcontrib>Kemp, Thomas</creatorcontrib><creatorcontrib>Abella, Antoni</creatorcontrib><creatorcontrib>Sony Deutschland GmbH</creatorcontrib><collection>USPTO Issued Patents</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tato, Raquel</au><au>Kemp, Thomas</au><au>Abella, Antoni</au><aucorp>Sony Deutschland GmbH</aucorp><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Pre-processing speech for speech recognition</title><date>2008-05-20</date><risdate>2008</risdate><abstract>A method for pre-processing speech, in particular for recognizing speech, including receiving a speech signal, separating a spectrum of said speech signal into a number of predetermined frequency sub-bands, analyzing said speech signal within each of said frequency sub-bands, generating respective band-dependent acoustic feature data for each of said respective frequency sub-bands, deriving band-dependent likelihoods for occurrences of speech elements or within said speech signal based on said band-dependent acoustic feature data, analyzing said speech signal within said spectrum, generating full-band acoustic feature data, which are at least in part representative for said speech signal with respect to said spectrum, deriving a full-band likelihood for occurrences of speech elements or of sequences thereof within said speech signal based on said full-band acoustic feature data, deriving an overall likelihood for occurrences of speech elements within said speech signal based on said band-dependent likelihoods and said full-band likelihood.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_uspatents_grants_07376559
source USPTO Issued Patents
title Pre-processing speech 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=2025-01-04T07%3A48%3A54IST&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=Tato,%20Raquel&rft.aucorp=Sony%20Deutschland%20GmbH&rft.date=2008-05-20&rft_id=info:doi/&rft_dat=%3Cuspatents_EFH%3E07376559%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