Speaker clustering using vector quantization and spectral clustering

We present a speaker clustering method for conversational speech recordings that contain short utterances from multiple speakers. The proposed method represents a speech segment with a vector of VQ code frequencies and uses a cosine between two vectors as their similarity measure. The clustering is...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Iso, K
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 4989
container_issue
container_start_page 4986
container_title
container_volume
creator Iso, K
description We present a speaker clustering method for conversational speech recordings that contain short utterances from multiple speakers. The proposed method represents a speech segment with a vector of VQ code frequencies and uses a cosine between two vectors as their similarity measure. The clustering is performed by a spectral clustering algorithm with cluster number estimation based on an eigen structure of the similarity matrix. We conducted experiments on five test sets with different utterance length distributions to compare the proposed method with the conventional approach based on a hierarchical agglomerative clustering using BIC stopping criterion. The results show that the proposed method significantly outperforms the conventional one in speaker diarization error rate and purity metrics.
doi_str_mv 10.1109/ICASSP.2010.5495078
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5495078</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5495078</ieee_id><sourcerecordid>5495078</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-6a5e3da706e954de639ed5ddab3af155aeea0643ff662fac940515366dc8c3f3</originalsourceid><addsrcrecordid>eNpVUM1Kw0AYXP_AWPsEveQFUvfv22SPUq0KBYX04K18Zr-V1ZjG3VTQpzdiD3qZgRlmGIaxmeBzIbi9uFtc1vXDXPJRAG2Bl9UBm9qyElpqraU15pBlUpW2EJY_Hv3zwB6zTIDkhRHanrKzlF4451Wpq4xd1T3hK8W8aXdpoBi653yXfvCDmmEb8_cddkP4wiFsuxw7l6d-NCK2fxLn7MRjm2i65wlbL6_Xi9tidX8zTl8VQZQwFAaBlMOSG7KgHRllyYFz-KTQCwAkQm608t4Y6bGxmoMAZYxrqkZ5NWGz39pARJs-hjeMn5v9H-obBZ1SEg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Speaker clustering using vector quantization and spectral clustering</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Iso, K</creator><creatorcontrib>Iso, K</creatorcontrib><description>We present a speaker clustering method for conversational speech recordings that contain short utterances from multiple speakers. The proposed method represents a speech segment with a vector of VQ code frequencies and uses a cosine between two vectors as their similarity measure. The clustering is performed by a spectral clustering algorithm with cluster number estimation based on an eigen structure of the similarity matrix. We conducted experiments on five test sets with different utterance length distributions to compare the proposed method with the conventional approach based on a hierarchical agglomerative clustering using BIC stopping criterion. The results show that the proposed method significantly outperforms the conventional one in speaker diarization error rate and purity metrics.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424442959</identifier><identifier>ISBN: 1424442958</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9781424442966</identifier><identifier>EISBN: 1424442966</identifier><identifier>DOI: 10.1109/ICASSP.2010.5495078</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bayesian information criterion ; Bayesian methods ; Broadcasting ; Clustering algorithms ; Clustering methods ; Frequency ; hierarchical agglomerative clustering ; Poles and towers ; Robustness ; speaker clustering ; spectral clustering ; Speech ; Testing ; Vector quantization</subject><ispartof>2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010, p.4986-4989</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5495078$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5495078$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Iso, K</creatorcontrib><title>Speaker clustering using vector quantization and spectral clustering</title><title>2010 IEEE International Conference on Acoustics, Speech and Signal Processing</title><addtitle>ICASSP</addtitle><description>We present a speaker clustering method for conversational speech recordings that contain short utterances from multiple speakers. The proposed method represents a speech segment with a vector of VQ code frequencies and uses a cosine between two vectors as their similarity measure. The clustering is performed by a spectral clustering algorithm with cluster number estimation based on an eigen structure of the similarity matrix. We conducted experiments on five test sets with different utterance length distributions to compare the proposed method with the conventional approach based on a hierarchical agglomerative clustering using BIC stopping criterion. The results show that the proposed method significantly outperforms the conventional one in speaker diarization error rate and purity metrics.</description><subject>Bayesian information criterion</subject><subject>Bayesian methods</subject><subject>Broadcasting</subject><subject>Clustering algorithms</subject><subject>Clustering methods</subject><subject>Frequency</subject><subject>hierarchical agglomerative clustering</subject><subject>Poles and towers</subject><subject>Robustness</subject><subject>speaker clustering</subject><subject>spectral clustering</subject><subject>Speech</subject><subject>Testing</subject><subject>Vector quantization</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424442959</isbn><isbn>1424442958</isbn><isbn>9781424442966</isbn><isbn>1424442966</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVUM1Kw0AYXP_AWPsEveQFUvfv22SPUq0KBYX04K18Zr-V1ZjG3VTQpzdiD3qZgRlmGIaxmeBzIbi9uFtc1vXDXPJRAG2Bl9UBm9qyElpqraU15pBlUpW2EJY_Hv3zwB6zTIDkhRHanrKzlF4451Wpq4xd1T3hK8W8aXdpoBi653yXfvCDmmEb8_cddkP4wiFsuxw7l6d-NCK2fxLn7MRjm2i65wlbL6_Xi9tidX8zTl8VQZQwFAaBlMOSG7KgHRllyYFz-KTQCwAkQm608t4Y6bGxmoMAZYxrqkZ5NWGz39pARJs-hjeMn5v9H-obBZ1SEg</recordid><startdate>201003</startdate><enddate>201003</enddate><creator>Iso, K</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201003</creationdate><title>Speaker clustering using vector quantization and spectral clustering</title><author>Iso, K</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-6a5e3da706e954de639ed5ddab3af155aeea0643ff662fac940515366dc8c3f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Bayesian information criterion</topic><topic>Bayesian methods</topic><topic>Broadcasting</topic><topic>Clustering algorithms</topic><topic>Clustering methods</topic><topic>Frequency</topic><topic>hierarchical agglomerative clustering</topic><topic>Poles and towers</topic><topic>Robustness</topic><topic>speaker clustering</topic><topic>spectral clustering</topic><topic>Speech</topic><topic>Testing</topic><topic>Vector quantization</topic><toplevel>online_resources</toplevel><creatorcontrib>Iso, K</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Iso, K</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Speaker clustering using vector quantization and spectral clustering</atitle><btitle>2010 IEEE International Conference on Acoustics, Speech and Signal Processing</btitle><stitle>ICASSP</stitle><date>2010-03</date><risdate>2010</risdate><spage>4986</spage><epage>4989</epage><pages>4986-4989</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424442959</isbn><isbn>1424442958</isbn><eisbn>9781424442966</eisbn><eisbn>1424442966</eisbn><abstract>We present a speaker clustering method for conversational speech recordings that contain short utterances from multiple speakers. The proposed method represents a speech segment with a vector of VQ code frequencies and uses a cosine between two vectors as their similarity measure. The clustering is performed by a spectral clustering algorithm with cluster number estimation based on an eigen structure of the similarity matrix. We conducted experiments on five test sets with different utterance length distributions to compare the proposed method with the conventional approach based on a hierarchical agglomerative clustering using BIC stopping criterion. The results show that the proposed method significantly outperforms the conventional one in speaker diarization error rate and purity metrics.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2010.5495078</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1520-6149
ispartof 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010, p.4986-4989
issn 1520-6149
2379-190X
language eng
recordid cdi_ieee_primary_5495078
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Bayesian information criterion
Bayesian methods
Broadcasting
Clustering algorithms
Clustering methods
Frequency
hierarchical agglomerative clustering
Poles and towers
Robustness
speaker clustering
spectral clustering
Speech
Testing
Vector quantization
title Speaker clustering using vector quantization and spectral clustering
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T08%3A32%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Speaker%20clustering%20using%20vector%20quantization%20and%20spectral%20clustering&rft.btitle=2010%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing&rft.au=Iso,%20K&rft.date=2010-03&rft.spage=4986&rft.epage=4989&rft.pages=4986-4989&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424442959&rft.isbn_list=1424442958&rft_id=info:doi/10.1109/ICASSP.2010.5495078&rft_dat=%3Cieee_6IE%3E5495078%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424442966&rft.eisbn_list=1424442966&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5495078&rfr_iscdi=true