Online reverberation time and clarity estimation in dynamic acoustic conditions

Online reverberation time and clarity estimation in dynamic acoustic conditions

Previously proposed methods for estimating acoustic parameters from reverberant, noisy speech signals exhibit insufficient performance under changing acoustic conditions. A data-centric approach is proposed to overcome the limiting assumption of fixed source–receiver transmission paths. The obtained...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of the Acoustical Society of America 2023-06, Vol.153 (6), p.3532-3542
Hauptverfasser: Götz, Philipp, Tuna, Cagdas, Walther, Andreas, Habets, Emanuël A. P.
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 3542
container_issue 6
container_start_page 3532
container_title The Journal of the Acoustical Society of America
container_volume 153
creator Götz, Philipp
Tuna, Cagdas
Walther, Andreas
Habets, Emanuël A. P.
description Previously proposed methods for estimating acoustic parameters from reverberant, noisy speech signals exhibit insufficient performance under changing acoustic conditions. A data-centric approach is proposed to overcome the limiting assumption of fixed source–receiver transmission paths. The obtained solution significantly enlarges the scope of potential applications for such estimators. The joint estimation of reverberation time RT60 and clarity index C50 in multiple frequency bands is studied with a focus on dynamic acoustic environments. Three different convolutional recurrent neural network architectures are considered to solve the tasks of single-band, multi-band, and multi-task parameter estimation. A comprehensive performance evaluation is provided that highlights the benefits of the proposed approach.
doi_str_mv 10.1121/10.0019804
format Article
fullrecord <record><control><sourceid>proquest_scita</sourceid><recordid>TN_cdi_proquest_miscellaneous_2832574031</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2832574031</sourcerecordid><originalsourceid>FETCH-LOGICAL-c359t-15e86bdd6a34b2aaeded0c195ca24516ecd14740a589c2142605e636a4aadf983</originalsourceid><addsrcrecordid>eNp9kEtLAzEUhYMotlY3_gDJUpTRvJtZSvEFhW50PWSSOxCZydRkKvTfmzpV3OjqcO_5ONx7EDqn5IZSRm-zEkJLTcQBmlLJSKElE4doSvK6EKVSE3SS0lsepeblMZrwOddzKdgUrVah9QFwhA-INUQz-D7gwXeATXDYtib6YYsh5dXo-YDdNpjOW2xsv8mGxbYPzu_cdIqOGtMmONvrDL0-3L8snorl6vF5cbcsLJflUFAJWtXOKcNFzYwBB45YWkprmJBUgXVUzAUxUpeWUcEUkaC4MsIY15Saz9DlmLuO_fsmn1d1PlloWxMgH1UxzZnMAZxm9GpEbexTitBU65ifiduKkmpX4E73BWb4Yp-7qTtwP-h3Yxm4HoFk_fDVyP9xf9IfffxFVmvX8E_nAofQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2832574031</pqid></control><display><type>article</type><title>Online reverberation time and clarity estimation in dynamic acoustic conditions</title><source>AIP Journals Complete</source><source>Alma/SFX Local Collection</source><source>AIP Acoustical Society of America</source><creator>Götz, Philipp ; Tuna, Cagdas ; Walther, Andreas ; Habets, Emanuël A. P.</creator><creatorcontrib>Götz, Philipp ; Tuna, Cagdas ; Walther, Andreas ; Habets, Emanuël A. P.</creatorcontrib><description>Previously proposed methods for estimating acoustic parameters from reverberant, noisy speech signals exhibit insufficient performance under changing acoustic conditions. A data-centric approach is proposed to overcome the limiting assumption of fixed source–receiver transmission paths. The obtained solution significantly enlarges the scope of potential applications for such estimators. The joint estimation of reverberation time RT60 and clarity index C50 in multiple frequency bands is studied with a focus on dynamic acoustic environments. Three different convolutional recurrent neural network architectures are considered to solve the tasks of single-band, multi-band, and multi-task parameter estimation. A comprehensive performance evaluation is provided that highlights the benefits of the proposed approach.</description><identifier>ISSN: 0001-4966</identifier><identifier>EISSN: 1520-8524</identifier><identifier>DOI: 10.1121/10.0019804</identifier><identifier>PMID: 37387542</identifier><identifier>CODEN: JASMAN</identifier><language>eng</language><publisher>United States</publisher><ispartof>The Journal of the Acoustical Society of America, 2023-06, Vol.153 (6), p.3532-3542</ispartof><rights>Acoustical Society of America</rights><rights>2023 Acoustical Society of America.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c359t-15e86bdd6a34b2aaeded0c195ca24516ecd14740a589c2142605e636a4aadf983</citedby><cites>FETCH-LOGICAL-c359t-15e86bdd6a34b2aaeded0c195ca24516ecd14740a589c2142605e636a4aadf983</cites><orcidid>0000-0002-6374-2242 ; 0000-0003-1817-5565 ; 0000-0002-2613-8046</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/jasa/article-lookup/doi/10.1121/10.0019804$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>207,208,314,776,780,790,1559,4498,27901,27902,76126</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37387542$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Götz, Philipp</creatorcontrib><creatorcontrib>Tuna, Cagdas</creatorcontrib><creatorcontrib>Walther, Andreas</creatorcontrib><creatorcontrib>Habets, Emanuël A. P.</creatorcontrib><title>Online reverberation time and clarity estimation in dynamic acoustic conditions</title><title>The Journal of the Acoustical Society of America</title><addtitle>J Acoust Soc Am</addtitle><description>Previously proposed methods for estimating acoustic parameters from reverberant, noisy speech signals exhibit insufficient performance under changing acoustic conditions. A data-centric approach is proposed to overcome the limiting assumption of fixed source–receiver transmission paths. The obtained solution significantly enlarges the scope of potential applications for such estimators. The joint estimation of reverberation time RT60 and clarity index C50 in multiple frequency bands is studied with a focus on dynamic acoustic environments. Three different convolutional recurrent neural network architectures are considered to solve the tasks of single-band, multi-band, and multi-task parameter estimation. A comprehensive performance evaluation is provided that highlights the benefits of the proposed approach.</description><issn>0001-4966</issn><issn>1520-8524</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kEtLAzEUhYMotlY3_gDJUpTRvJtZSvEFhW50PWSSOxCZydRkKvTfmzpV3OjqcO_5ONx7EDqn5IZSRm-zEkJLTcQBmlLJSKElE4doSvK6EKVSE3SS0lsepeblMZrwOddzKdgUrVah9QFwhA-INUQz-D7gwXeATXDYtib6YYsh5dXo-YDdNpjOW2xsv8mGxbYPzu_cdIqOGtMmONvrDL0-3L8snorl6vF5cbcsLJflUFAJWtXOKcNFzYwBB45YWkprmJBUgXVUzAUxUpeWUcEUkaC4MsIY15Saz9DlmLuO_fsmn1d1PlloWxMgH1UxzZnMAZxm9GpEbexTitBU65ifiduKkmpX4E73BWb4Yp-7qTtwP-h3Yxm4HoFk_fDVyP9xf9IfffxFVmvX8E_nAofQ</recordid><startdate>202306</startdate><enddate>202306</enddate><creator>Götz, Philipp</creator><creator>Tuna, Cagdas</creator><creator>Walther, Andreas</creator><creator>Habets, Emanuël A. P.</creator><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-6374-2242</orcidid><orcidid>https://orcid.org/0000-0003-1817-5565</orcidid><orcidid>https://orcid.org/0000-0002-2613-8046</orcidid></search><sort><creationdate>202306</creationdate><title>Online reverberation time and clarity estimation in dynamic acoustic conditions</title><author>Götz, Philipp ; Tuna, Cagdas ; Walther, Andreas ; Habets, Emanuël A. P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c359t-15e86bdd6a34b2aaeded0c195ca24516ecd14740a589c2142605e636a4aadf983</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Götz, Philipp</creatorcontrib><creatorcontrib>Tuna, Cagdas</creatorcontrib><creatorcontrib>Walther, Andreas</creatorcontrib><creatorcontrib>Habets, Emanuël A. P.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>The Journal of the Acoustical Society of America</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Götz, Philipp</au><au>Tuna, Cagdas</au><au>Walther, Andreas</au><au>Habets, Emanuël A. P.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Online reverberation time and clarity estimation in dynamic acoustic conditions</atitle><jtitle>The Journal of the Acoustical Society of America</jtitle><addtitle>J Acoust Soc Am</addtitle><date>2023-06</date><risdate>2023</risdate><volume>153</volume><issue>6</issue><spage>3532</spage><epage>3542</epage><pages>3532-3542</pages><issn>0001-4966</issn><eissn>1520-8524</eissn><coden>JASMAN</coden><abstract>Previously proposed methods for estimating acoustic parameters from reverberant, noisy speech signals exhibit insufficient performance under changing acoustic conditions. A data-centric approach is proposed to overcome the limiting assumption of fixed source–receiver transmission paths. The obtained solution significantly enlarges the scope of potential applications for such estimators. The joint estimation of reverberation time RT60 and clarity index C50 in multiple frequency bands is studied with a focus on dynamic acoustic environments. Three different convolutional recurrent neural network architectures are considered to solve the tasks of single-band, multi-band, and multi-task parameter estimation. A comprehensive performance evaluation is provided that highlights the benefits of the proposed approach.</abstract><cop>United States</cop><pmid>37387542</pmid><doi>10.1121/10.0019804</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-6374-2242</orcidid><orcidid>https://orcid.org/0000-0003-1817-5565</orcidid><orcidid>https://orcid.org/0000-0002-2613-8046</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0001-4966
ispartof The Journal of the Acoustical Society of America, 2023-06, Vol.153 (6), p.3532-3542
issn 0001-4966
1520-8524
language eng
recordid cdi_proquest_miscellaneous_2832574031
source AIP Journals Complete; Alma/SFX Local Collection; AIP Acoustical Society of America
title Online reverberation time and clarity estimation in dynamic acoustic conditions
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T00%3A54%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_scita&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Online%20reverberation%20time%20and%20clarity%20estimation%20in%20dynamic%20acoustic%20conditions&rft.jtitle=The%20Journal%20of%20the%20Acoustical%20Society%20of%20America&rft.au=G%C3%B6tz,%20Philipp&rft.date=2023-06&rft.volume=153&rft.issue=6&rft.spage=3532&rft.epage=3542&rft.pages=3532-3542&rft.issn=0001-4966&rft.eissn=1520-8524&rft.coden=JASMAN&rft_id=info:doi/10.1121/10.0019804&rft_dat=%3Cproquest_scita%3E2832574031%3C/proquest_scita%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2832574031&rft_id=info:pmid/37387542&rfr_iscdi=true