Speaker adaptive speech recognition

A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and ac...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	NEUMEYER, LEONARDO, RTISCHEV, DIMITRY, DIGALAKIS, VASSILIOS
Format:	Patent
Sprache:	eng ; fre ; ger
Schlagworte:	ACOUSTICS MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION
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	NEUMEYER, LEONARDO RTISCHEV, DIMITRY DIGALAKIS, VASSILIOS
description	A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and achieve better recognition accuracy than non-adapted models. In a further embodiment, the transformation-based adaptation technique is combined with a known Bayesian adaptation technique.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP0804721A2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP0804721A2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP0804721A23</originalsourceid><addsrcrecordid>eNrjZFAOLkhNzE4tUkhMSSwoySxLVSguSE1NzlAoSk3OT8_LLMnMz-NhYE1LzClO5YXS3AwKbq4hzh66qQX58anFBYnJqXmpJfGuAQYWBibmRoaORsZEKAEAqWYmMg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Speaker adaptive speech recognition</title><source>esp@cenet</source><creator>NEUMEYER, LEONARDO ; RTISCHEV, DIMITRY ; DIGALAKIS, VASSILIOS</creator><creatorcontrib>NEUMEYER, LEONARDO ; RTISCHEV, DIMITRY ; DIGALAKIS, VASSILIOS</creatorcontrib><description>A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and achieve better recognition accuracy than non-adapted models. In a further embodiment, the transformation-based adaptation technique is combined with a known Bayesian adaptation technique.</description><edition>7</edition><language>eng ; fre ; ger</language><subject>ACOUSTICS ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>1997</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&date=19971105&DB=EPODOC&CC=EP&NR=0804721A2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=19971105&DB=EPODOC&CC=EP&NR=0804721A2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>NEUMEYER, LEONARDO</creatorcontrib><creatorcontrib>RTISCHEV, DIMITRY</creatorcontrib><creatorcontrib>DIGALAKIS, VASSILIOS</creatorcontrib><title>Speaker adaptive speech recognition</title><description>A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and achieve better recognition accuracy than non-adapted models. In a further embodiment, the transformation-based adaptation technique is combined with a known Bayesian adaptation technique.</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>1997</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFAOLkhNzE4tUkhMSSwoySxLVSguSE1NzlAoSk3OT8_LLMnMz-NhYE1LzClO5YXS3AwKbq4hzh66qQX58anFBYnJqXmpJfGuAQYWBibmRoaORsZEKAEAqWYmMg</recordid><startdate>19971105</startdate><enddate>19971105</enddate><creator>NEUMEYER, LEONARDO</creator><creator>RTISCHEV, DIMITRY</creator><creator>DIGALAKIS, VASSILIOS</creator><scope>EVB</scope></search><sort><creationdate>19971105</creationdate><title>Speaker adaptive speech recognition</title><author>NEUMEYER, LEONARDO ; RTISCHEV, DIMITRY ; DIGALAKIS, VASSILIOS</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP0804721A23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>1997</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>NEUMEYER, LEONARDO</creatorcontrib><creatorcontrib>RTISCHEV, DIMITRY</creatorcontrib><creatorcontrib>DIGALAKIS, VASSILIOS</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>NEUMEYER, LEONARDO</au><au>RTISCHEV, DIMITRY</au><au>DIGALAKIS, VASSILIOS</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Speaker adaptive speech recognition</title><date>1997-11-05</date><risdate>1997</risdate><abstract>A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and achieve better recognition accuracy than non-adapted models. In a further embodiment, the transformation-based adaptation technique is combined with a known Bayesian adaptation technique.</abstract><edition>7</edition><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng ; fre ; ger
recordid	cdi_epo_espacenet_EP0804721A2
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	Speaker adaptive speech recognition
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T12%3A54%3A36IST&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=NEUMEYER,%20LEONARDO&rft.date=1997-11-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP0804721A2%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