Stream-based speaker segmentation using speaker factors and eigenvoices
This paper presents a stream-based approach for unsupervised multi-speaker conversational speech segmentation. The main idea of this work is to exploit prior knowledge about the speaker space to find a low dimensional vector of speaker factors that summarize the salient speaker characteristics. This...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4136 |
|---|---|
| container_issue | |
| container_start_page | 4133 |
| container_title | |
| container_volume | |
| creator | Castaldo, F. Colibro, D. Dalmasso, E. Laface, P. Vair, C. |
| description | This paper presents a stream-based approach for unsupervised multi-speaker conversational speech segmentation. The main idea of this work is to exploit prior knowledge about the speaker space to find a low dimensional vector of speaker factors that summarize the salient speaker characteristics. This new approach produces segmentation error rates that are better than the state of the art ones reported in our previous work on the segmentation task in the NIST 2000 Speaker Recognition Evaluation (SRE). We also show how the performance of a speaker recognition system in the core test of the 2006 NIST SRE is affected, comparing the results obtained using single speaker and automatically segmented test data. |
| doi_str_mv | 10.1109/ICASSP.2008.4518564 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4518564</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4518564</ieee_id><sourcerecordid>4518564</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-7df615c1bb0835ea19152d49e29dde225f348d6e26d9130a51f029c242893d673</originalsourceid><addsrcrecordid>eNo9kM1Kw0AUhcc_sNY8QTd5gYlz5yeZu5SiVSgoRMFdmWRuwqhJSiYKvn0DVs_mLD44fBzGViAyAIE3j-vbsnzOpBA20wasyfUJuwIttQZtNZ6yhVQFckDxdsYSLOwfU-qcLcBIwXPQeMmSGN_FHG2UQbNgm3IayXW8cpF8GvfkPmhMI7Ud9ZObwtCnXzH07T9qXD0NY0xd71MKLfXfQ6gpXrOLxn1GSo69ZK_3dy_rB7592sz2Wx6gMBMvfJODqaGqhFWGHODs5jWSRO9JStMobX1OMvcISjgDjZBYSy0tKp8XaslWv7uBiHb7MXRu_NkdP1EHpOJRRA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Stream-based speaker segmentation using speaker factors and eigenvoices</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Castaldo, F. ; Colibro, D. ; Dalmasso, E. ; Laface, P. ; Vair, C.</creator><creatorcontrib>Castaldo, F. ; Colibro, D. ; Dalmasso, E. ; Laface, P. ; Vair, C.</creatorcontrib><description>This paper presents a stream-based approach for unsupervised multi-speaker conversational speech segmentation. The main idea of this work is to exploit prior knowledge about the speaker space to find a low dimensional vector of speaker factors that summarize the salient speaker characteristics. This new approach produces segmentation error rates that are better than the state of the art ones reported in our previous work on the segmentation task in the NIST 2000 Speaker Recognition Evaluation (SRE). We also show how the performance of a speaker recognition system in the core test of the 2006 NIST SRE is affected, comparing the results obtained using single speaker and automatically segmented test data.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424414833</identifier><identifier>ISBN: 1424414830</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 1424414849</identifier><identifier>EISBN: 9781424414840</identifier><identifier>DOI: 10.1109/ICASSP.2008.4518564</identifier><language>eng</language><publisher>IEEE</publisher><subject>Automatic testing ; Delay ; eigenvoices ; Error analysis ; NIST ; Performance analysis ; Signal analysis ; speaker clustering ; speaker factors ; Speaker modeling ; Speaker recognition ; speaker segmentation ; Speech ; Streaming media ; System testing</subject><ispartof>2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.4133-4136</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/4518564$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4518564$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Castaldo, F.</creatorcontrib><creatorcontrib>Colibro, D.</creatorcontrib><creatorcontrib>Dalmasso, E.</creatorcontrib><creatorcontrib>Laface, P.</creatorcontrib><creatorcontrib>Vair, C.</creatorcontrib><title>Stream-based speaker segmentation using speaker factors and eigenvoices</title><title>2008 IEEE International Conference on Acoustics, Speech and Signal Processing</title><addtitle>ICASSP</addtitle><description>This paper presents a stream-based approach for unsupervised multi-speaker conversational speech segmentation. The main idea of this work is to exploit prior knowledge about the speaker space to find a low dimensional vector of speaker factors that summarize the salient speaker characteristics. This new approach produces segmentation error rates that are better than the state of the art ones reported in our previous work on the segmentation task in the NIST 2000 Speaker Recognition Evaluation (SRE). We also show how the performance of a speaker recognition system in the core test of the 2006 NIST SRE is affected, comparing the results obtained using single speaker and automatically segmented test data.</description><subject>Automatic testing</subject><subject>Delay</subject><subject>eigenvoices</subject><subject>Error analysis</subject><subject>NIST</subject><subject>Performance analysis</subject><subject>Signal analysis</subject><subject>speaker clustering</subject><subject>speaker factors</subject><subject>Speaker modeling</subject><subject>Speaker recognition</subject><subject>speaker segmentation</subject><subject>Speech</subject><subject>Streaming media</subject><subject>System testing</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424414833</isbn><isbn>1424414830</isbn><isbn>1424414849</isbn><isbn>9781424414840</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo9kM1Kw0AUhcc_sNY8QTd5gYlz5yeZu5SiVSgoRMFdmWRuwqhJSiYKvn0DVs_mLD44fBzGViAyAIE3j-vbsnzOpBA20wasyfUJuwIttQZtNZ6yhVQFckDxdsYSLOwfU-qcLcBIwXPQeMmSGN_FHG2UQbNgm3IayXW8cpF8GvfkPmhMI7Ud9ZObwtCnXzH07T9qXD0NY0xd71MKLfXfQ6gpXrOLxn1GSo69ZK_3dy_rB7592sz2Wx6gMBMvfJODqaGqhFWGHODs5jWSRO9JStMobX1OMvcISjgDjZBYSy0tKp8XaslWv7uBiHb7MXRu_NkdP1EHpOJRRA</recordid><startdate>200803</startdate><enddate>200803</enddate><creator>Castaldo, F.</creator><creator>Colibro, D.</creator><creator>Dalmasso, E.</creator><creator>Laface, P.</creator><creator>Vair, C.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200803</creationdate><title>Stream-based speaker segmentation using speaker factors and eigenvoices</title><author>Castaldo, F. ; Colibro, D. ; Dalmasso, E. ; Laface, P. ; Vair, C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-7df615c1bb0835ea19152d49e29dde225f348d6e26d9130a51f029c242893d673</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Automatic testing</topic><topic>Delay</topic><topic>eigenvoices</topic><topic>Error analysis</topic><topic>NIST</topic><topic>Performance analysis</topic><topic>Signal analysis</topic><topic>speaker clustering</topic><topic>speaker factors</topic><topic>Speaker modeling</topic><topic>Speaker recognition</topic><topic>speaker segmentation</topic><topic>Speech</topic><topic>Streaming media</topic><topic>System testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Castaldo, F.</creatorcontrib><creatorcontrib>Colibro, D.</creatorcontrib><creatorcontrib>Dalmasso, E.</creatorcontrib><creatorcontrib>Laface, P.</creatorcontrib><creatorcontrib>Vair, C.</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>Castaldo, F.</au><au>Colibro, D.</au><au>Dalmasso, E.</au><au>Laface, P.</au><au>Vair, C.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Stream-based speaker segmentation using speaker factors and eigenvoices</atitle><btitle>2008 IEEE International Conference on Acoustics, Speech and Signal Processing</btitle><stitle>ICASSP</stitle><date>2008-03</date><risdate>2008</risdate><spage>4133</spage><epage>4136</epage><pages>4133-4136</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424414833</isbn><isbn>1424414830</isbn><eisbn>1424414849</eisbn><eisbn>9781424414840</eisbn><abstract>This paper presents a stream-based approach for unsupervised multi-speaker conversational speech segmentation. The main idea of this work is to exploit prior knowledge about the speaker space to find a low dimensional vector of speaker factors that summarize the salient speaker characteristics. This new approach produces segmentation error rates that are better than the state of the art ones reported in our previous work on the segmentation task in the NIST 2000 Speaker Recognition Evaluation (SRE). We also show how the performance of a speaker recognition system in the core test of the 2006 NIST SRE is affected, comparing the results obtained using single speaker and automatically segmented test data.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2008.4518564</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.4133-4136 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_4518564 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Automatic testing Delay eigenvoices Error analysis NIST Performance analysis Signal analysis speaker clustering speaker factors Speaker modeling Speaker recognition speaker segmentation Speech Streaming media System testing |
| title | Stream-based speaker segmentation using speaker factors and eigenvoices |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T09%3A21%3A07IST&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=Stream-based%20speaker%20segmentation%20using%20speaker%20factors%20and%20eigenvoices&rft.btitle=2008%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing&rft.au=Castaldo,%20F.&rft.date=2008-03&rft.spage=4133&rft.epage=4136&rft.pages=4133-4136&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424414833&rft.isbn_list=1424414830&rft_id=info:doi/10.1109/ICASSP.2008.4518564&rft_dat=%3Cieee_6IE%3E4518564%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424414849&rft.eisbn_list=9781424414840&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4518564&rfr_iscdi=true |