Subjective and Objective Quality Assessment of Audio Source Separation
We aim to assess the perceived quality of estimated source signals in the context of audio source separation. These signals may involve one or more kinds of distortions, including distortion of the target source, interference from the other sources or musical noise artifacts. We propose a subjective...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on audio, speech, and language processing speech, and language processing, 2011-09, Vol.19 (7), p.2046-2057 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2057 |
|---|---|
| container_issue | 7 |
| container_start_page | 2046 |
| container_title | IEEE transactions on audio, speech, and language processing |
| container_volume | 19 |
| creator | Emiya, V. Vincent, E. Harlander, N. Hohmann, V. |
| description | We aim to assess the perceived quality of estimated source signals in the context of audio source separation. These signals may involve one or more kinds of distortions, including distortion of the target source, interference from the other sources or musical noise artifacts. We propose a subjective test protocol to assess the perceived quality with respect to each kind of distortion and collect the scores of 20 subjects over 80 sounds. We then propose a family of objective measures aiming to predict these subjective scores based on the decomposition of the estimation error into several distortion components and on the use of the PEMO-Q perceptual salience measure to provide multiple features that are then combined. These measures increase correlation with subjective scores up to 0.5 compared to nonlinear mapping of individual state-of-the-art source separation measures. Finally, we released the data and code presented in this paper in a freely available toolkit called PEASS. |
| doi_str_mv | 10.1109/TASL.2011.2109381 |
| format | Article |
| fullrecord | <record><control><sourceid>hal_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TASL_2011_2109381</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5704564</ieee_id><sourcerecordid>oai_HAL_inria_00567152v1</sourcerecordid><originalsourceid>FETCH-LOGICAL-c440t-8a3dbe979b3a836244b8148d501a3db6ddbdb766d76d800c560f7965ff1c90e63</originalsourceid><addsrcrecordid>eNo9kE9Lw0AQxRdRsFY_gHjJxZO07iT7L8dQrBUCRVLPy2Z3g1vSpOwmBb-9CSk5zTzee8PwQ-gZ8BoAp--HrMjXMQZYx4NMBNygBVAqVjyNye28A7tHDyEcMSYJI7BA26Ivj1Z37mIj1ZhoP6vvXtWu-4uyEGwIJ9t0UVtFWW9cGxVt77WNCntWXnWubR7RXaXqYJ-uc4l-th-HzW6V7z-_Nlm-0oTgbiVUYkqb8rRMlEhYTEgpgAhDMYwOM6Y0JWfMcGYExpoyXPGU0aoCnWLLkiV6m-7-qlqevTsp_ydb5eQuy6VrvFMSY8o40PgCQxqmtPZtCN5WcwWwHLHJEZscsckrtqHzOnXOKmhVV1412oW5OLwsiGB8yL1MOWetnW3KMaGMJP9QKXVZ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Subjective and Objective Quality Assessment of Audio Source Separation</title><source>IEEE Electronic Library (IEL)</source><creator>Emiya, V. ; Vincent, E. ; Harlander, N. ; Hohmann, V.</creator><creatorcontrib>Emiya, V. ; Vincent, E. ; Harlander, N. ; Hohmann, V.</creatorcontrib><description>We aim to assess the perceived quality of estimated source signals in the context of audio source separation. These signals may involve one or more kinds of distortions, including distortion of the target source, interference from the other sources or musical noise artifacts. We propose a subjective test protocol to assess the perceived quality with respect to each kind of distortion and collect the scores of 20 subjects over 80 sounds. We then propose a family of objective measures aiming to predict these subjective scores based on the decomposition of the estimation error into several distortion components and on the use of the PEMO-Q perceptual salience measure to provide multiple features that are then combined. These measures increase correlation with subjective scores up to 0.5 compared to nonlinear mapping of individual state-of-the-art source separation measures. Finally, we released the data and code presented in this paper in a freely available toolkit called PEASS.</description><identifier>ISSN: 1558-7916</identifier><identifier>EISSN: 1558-7924</identifier><identifier>DOI: 10.1109/TASL.2011.2109381</identifier><identifier>CODEN: ITASD8</identifier><language>eng</language><publisher>Piscataway, NJ: IEEE</publisher><subject>Applied sciences ; Audio ; Computer Science ; Detection, estimation, filtering, equalization, prediction ; Distortion measurement ; Engineering Sciences ; Exact sciences and technology ; Information, signal and communications theory ; Noise ; Nonlinear distortion ; objective measure ; Protocols ; quality assessment ; Signal and communications theory ; Signal and Image Processing ; Signal, noise ; Source separation ; Speech ; subjective test protocol ; Telecommunications and information theory</subject><ispartof>IEEE transactions on audio, speech, and language processing, 2011-09, Vol.19 (7), p.2046-2057</ispartof><rights>2015 INIST-CNRS</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c440t-8a3dbe979b3a836244b8148d501a3db6ddbdb766d76d800c560f7965ff1c90e63</citedby><cites>FETCH-LOGICAL-c440t-8a3dbe979b3a836244b8148d501a3db6ddbdb766d76d800c560f7965ff1c90e63</cites><orcidid>0000-0001-7102-6943 ; 0000-0002-0183-7289</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5704564$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,314,776,780,792,881,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5704564$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=24484867$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://inria.hal.science/inria-00567152$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Emiya, V.</creatorcontrib><creatorcontrib>Vincent, E.</creatorcontrib><creatorcontrib>Harlander, N.</creatorcontrib><creatorcontrib>Hohmann, V.</creatorcontrib><title>Subjective and Objective Quality Assessment of Audio Source Separation</title><title>IEEE transactions on audio, speech, and language processing</title><addtitle>TASL</addtitle><description>We aim to assess the perceived quality of estimated source signals in the context of audio source separation. These signals may involve one or more kinds of distortions, including distortion of the target source, interference from the other sources or musical noise artifacts. We propose a subjective test protocol to assess the perceived quality with respect to each kind of distortion and collect the scores of 20 subjects over 80 sounds. We then propose a family of objective measures aiming to predict these subjective scores based on the decomposition of the estimation error into several distortion components and on the use of the PEMO-Q perceptual salience measure to provide multiple features that are then combined. These measures increase correlation with subjective scores up to 0.5 compared to nonlinear mapping of individual state-of-the-art source separation measures. Finally, we released the data and code presented in this paper in a freely available toolkit called PEASS.</description><subject>Applied sciences</subject><subject>Audio</subject><subject>Computer Science</subject><subject>Detection, estimation, filtering, equalization, prediction</subject><subject>Distortion measurement</subject><subject>Engineering Sciences</subject><subject>Exact sciences and technology</subject><subject>Information, signal and communications theory</subject><subject>Noise</subject><subject>Nonlinear distortion</subject><subject>objective measure</subject><subject>Protocols</subject><subject>quality assessment</subject><subject>Signal and communications theory</subject><subject>Signal and Image Processing</subject><subject>Signal, noise</subject><subject>Source separation</subject><subject>Speech</subject><subject>subjective test protocol</subject><subject>Telecommunications and information theory</subject><issn>1558-7916</issn><issn>1558-7924</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE9Lw0AQxRdRsFY_gHjJxZO07iT7L8dQrBUCRVLPy2Z3g1vSpOwmBb-9CSk5zTzee8PwQ-gZ8BoAp--HrMjXMQZYx4NMBNygBVAqVjyNye28A7tHDyEcMSYJI7BA26Ivj1Z37mIj1ZhoP6vvXtWu-4uyEGwIJ9t0UVtFWW9cGxVt77WNCntWXnWubR7RXaXqYJ-uc4l-th-HzW6V7z-_Nlm-0oTgbiVUYkqb8rRMlEhYTEgpgAhDMYwOM6Y0JWfMcGYExpoyXPGU0aoCnWLLkiV6m-7-qlqevTsp_ydb5eQuy6VrvFMSY8o40PgCQxqmtPZtCN5WcwWwHLHJEZscsckrtqHzOnXOKmhVV1412oW5OLwsiGB8yL1MOWetnW3KMaGMJP9QKXVZ</recordid><startdate>20110901</startdate><enddate>20110901</enddate><creator>Emiya, V.</creator><creator>Vincent, E.</creator><creator>Harlander, N.</creator><creator>Hohmann, V.</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0001-7102-6943</orcidid><orcidid>https://orcid.org/0000-0002-0183-7289</orcidid></search><sort><creationdate>20110901</creationdate><title>Subjective and Objective Quality Assessment of Audio Source Separation</title><author>Emiya, V. ; Vincent, E. ; Harlander, N. ; Hohmann, V.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c440t-8a3dbe979b3a836244b8148d501a3db6ddbdb766d76d800c560f7965ff1c90e63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Applied sciences</topic><topic>Audio</topic><topic>Computer Science</topic><topic>Detection, estimation, filtering, equalization, prediction</topic><topic>Distortion measurement</topic><topic>Engineering Sciences</topic><topic>Exact sciences and technology</topic><topic>Information, signal and communications theory</topic><topic>Noise</topic><topic>Nonlinear distortion</topic><topic>objective measure</topic><topic>Protocols</topic><topic>quality assessment</topic><topic>Signal and communications theory</topic><topic>Signal and Image Processing</topic><topic>Signal, noise</topic><topic>Source separation</topic><topic>Speech</topic><topic>subjective test protocol</topic><topic>Telecommunications and information theory</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Emiya, V.</creatorcontrib><creatorcontrib>Vincent, E.</creatorcontrib><creatorcontrib>Harlander, N.</creatorcontrib><creatorcontrib>Hohmann, V.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>IEEE transactions on audio, speech, and language processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Emiya, V.</au><au>Vincent, E.</au><au>Harlander, N.</au><au>Hohmann, V.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Subjective and Objective Quality Assessment of Audio Source Separation</atitle><jtitle>IEEE transactions on audio, speech, and language processing</jtitle><stitle>TASL</stitle><date>2011-09-01</date><risdate>2011</risdate><volume>19</volume><issue>7</issue><spage>2046</spage><epage>2057</epage><pages>2046-2057</pages><issn>1558-7916</issn><eissn>1558-7924</eissn><coden>ITASD8</coden><abstract>We aim to assess the perceived quality of estimated source signals in the context of audio source separation. These signals may involve one or more kinds of distortions, including distortion of the target source, interference from the other sources or musical noise artifacts. We propose a subjective test protocol to assess the perceived quality with respect to each kind of distortion and collect the scores of 20 subjects over 80 sounds. We then propose a family of objective measures aiming to predict these subjective scores based on the decomposition of the estimation error into several distortion components and on the use of the PEMO-Q perceptual salience measure to provide multiple features that are then combined. These measures increase correlation with subjective scores up to 0.5 compared to nonlinear mapping of individual state-of-the-art source separation measures. Finally, we released the data and code presented in this paper in a freely available toolkit called PEASS.</abstract><cop>Piscataway, NJ</cop><pub>IEEE</pub><doi>10.1109/TASL.2011.2109381</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-7102-6943</orcidid><orcidid>https://orcid.org/0000-0002-0183-7289</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1558-7916 |
| ispartof | IEEE transactions on audio, speech, and language processing, 2011-09, Vol.19 (7), p.2046-2057 |
| issn | 1558-7916 1558-7924 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TASL_2011_2109381 |
| source | IEEE Electronic Library (IEL) |
| subjects | Applied sciences Audio Computer Science Detection, estimation, filtering, equalization, prediction Distortion measurement Engineering Sciences Exact sciences and technology Information, signal and communications theory Noise Nonlinear distortion objective measure Protocols quality assessment Signal and communications theory Signal and Image Processing Signal, noise Source separation Speech subjective test protocol Telecommunications and information theory |
| title | Subjective and Objective Quality Assessment of Audio Source Separation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T12%3A25%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-hal_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Subjective%20and%20Objective%20Quality%20Assessment%20of%20Audio%20Source%20Separation&rft.jtitle=IEEE%20transactions%20on%20audio,%20speech,%20and%20language%20processing&rft.au=Emiya,%20V.&rft.date=2011-09-01&rft.volume=19&rft.issue=7&rft.spage=2046&rft.epage=2057&rft.pages=2046-2057&rft.issn=1558-7916&rft.eissn=1558-7924&rft.coden=ITASD8&rft_id=info:doi/10.1109/TASL.2011.2109381&rft_dat=%3Chal_RIE%3Eoai_HAL_inria_00567152v1%3C/hal_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5704564&rfr_iscdi=true |