Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure

Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Siqi, Suo, Hongbin
Format: Artikel
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 Zheng, Siqi
Suo, Hongbin
description Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and agglomerative hierarchical clustering only take into account properties such as proximity and relative densities. In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered. This work has four major contributions. First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we propose to use uniform manifold approximation to reduce dimension while retaining global and local topological structure. Third, a masked filtering approach is introduced to extract "clean" speaker embeddings. Finally, the community structure is applied to an end-to-end post-processing network to obtain diarization results. The final system presents a relative DER reduction of up to 70 percent. The breakdown contribution of each component is analyzed.
doi_str_mv 10.48550/arxiv.2204.12112
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2204_12112</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2204_12112</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-6863cc171e7e5006c76df488c6f79b45fe4a63a71eaea91c6b88fe399d2829273</originalsourceid><addsrcrecordid>eNotj8tqwzAUBbXpoiT9gK6qH7BrybIkL4OTPiAQaAxdmhvlKhG1LSPLpenXN3W7OjAHBoaQe5alQhdF9gjhy32mnGciZZwxfkuaN7Q-dFML0fUnuh8QPjDQtYPgvq_M9xRGWvmum3oXL3SNEc2M31080003nGF0I931tPaDb_3JGWjpPobJxCngktxYaEe8-98FqZ82dfWSbHfPr9Vqm4BUPJFa5sYwxVBhkWXSKHm0QmsjrSoPorAoQOZw_QGhZEYetLaYl-WRa15ylS_Iw592LmyG4DoIl-a3tJlL8x8P2U_A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure</title><source>arXiv.org</source><creator>Zheng, Siqi ; Suo, Hongbin</creator><creatorcontrib>Zheng, Siqi ; Suo, Hongbin</creatorcontrib><description>Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and agglomerative hierarchical clustering only take into account properties such as proximity and relative densities. In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered. This work has four major contributions. First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we propose to use uniform manifold approximation to reduce dimension while retaining global and local topological structure. Third, a masked filtering approach is introduced to extract "clean" speaker embeddings. Finally, the community structure is applied to an end-to-end post-processing network to obtain diarization results. The final system presents a relative DER reduction of up to 70 percent. The breakdown contribution of each component is analyzed.</description><identifier>DOI: 10.48550/arxiv.2204.12112</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Sound</subject><creationdate>2022-04</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2204.12112$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2204.12112$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zheng, Siqi</creatorcontrib><creatorcontrib>Suo, Hongbin</creatorcontrib><title>Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure</title><description>Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and agglomerative hierarchical clustering only take into account properties such as proximity and relative densities. In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered. This work has four major contributions. First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we propose to use uniform manifold approximation to reduce dimension while retaining global and local topological structure. Third, a masked filtering approach is introduced to extract "clean" speaker embeddings. Finally, the community structure is applied to an end-to-end post-processing network to obtain diarization results. The final system presents a relative DER reduction of up to 70 percent. The breakdown contribution of each component is analyzed.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwzAUBbXpoiT9gK6qH7BrybIkL4OTPiAQaAxdmhvlKhG1LSPLpenXN3W7OjAHBoaQe5alQhdF9gjhy32mnGciZZwxfkuaN7Q-dFML0fUnuh8QPjDQtYPgvq_M9xRGWvmum3oXL3SNEc2M31080003nGF0I931tPaDb_3JGWjpPobJxCngktxYaEe8-98FqZ82dfWSbHfPr9Vqm4BUPJFa5sYwxVBhkWXSKHm0QmsjrSoPorAoQOZw_QGhZEYetLaYl-WRa15ylS_Iw592LmyG4DoIl-a3tJlL8x8P2U_A</recordid><startdate>20220426</startdate><enddate>20220426</enddate><creator>Zheng, Siqi</creator><creator>Suo, Hongbin</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220426</creationdate><title>Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure</title><author>Zheng, Siqi ; Suo, Hongbin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-6863cc171e7e5006c76df488c6f79b45fe4a63a71eaea91c6b88fe399d2829273</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Siqi</creatorcontrib><creatorcontrib>Suo, Hongbin</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zheng, Siqi</au><au>Suo, Hongbin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure</atitle><date>2022-04-26</date><risdate>2022</risdate><abstract>Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and agglomerative hierarchical clustering only take into account properties such as proximity and relative densities. In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered. This work has four major contributions. First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we propose to use uniform manifold approximation to reduce dimension while retaining global and local topological structure. Third, a masked filtering approach is introduced to extract "clean" speaker embeddings. Finally, the community structure is applied to an end-to-end post-processing network to obtain diarization results. The final system presents a relative DER reduction of up to 70 percent. The breakdown contribution of each component is analyzed.</abstract><doi>10.48550/arxiv.2204.12112</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2204.12112
ispartof
issn
language eng
recordid cdi_arxiv_primary_2204_12112
source arXiv.org
subjects Computer Science - Learning
Computer Science - Sound
title Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T14%3A24%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Reformulating%20Speaker%20Diarization%20as%20Community%20Detection%20With%20Emphasis%20On%20Topological%20Structure&rft.au=Zheng,%20Siqi&rft.date=2022-04-26&rft_id=info:doi/10.48550/arxiv.2204.12112&rft_dat=%3Carxiv_GOX%3E2204_12112%3C/arxiv_GOX%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