{"id":"https://openalex.org/W2971417062","doi":"https://doi.org/10.1109/taslp.2020.2968738","title":"On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement","display_name":"On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2971417062","doi":"https://doi.org/10.1109/taslp.2020.2968738","mag":"2971417062"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2968738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2968738","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.01019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Morten Kolb\u00e6k","orcid":"https://orcid.org/0000-0002-2561-4960"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Morten Kolb\u00e6k","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-2561-4960","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng-Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-6856-8928","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":null,"display_name":"S\u00f8ren Holdt Jensen","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"S\u00f8ren Holdt Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jesper Jensen","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":10.8391,"has_fulltext":true,"cited_by_count":125,"citation_normalized_percentile":{"value":0.99036907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"825","last_page":"838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8823999762535095},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7177000045776367},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4352000057697296},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43059998750686646},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3693000078201294},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3458000123500824},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.33640000224113464},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3361000120639801}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8823999762535095},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7177000045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6603999733924866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6523000001907349},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C3018181011","wikidata":"https://www.wikidata.org/wiki/Q6849688","display_name":"Contrast enhancement","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.2968738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2968738","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1909.01019","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.01019","pdf_url":"https://arxiv.org/pdf/1909.01019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/fcb0de6e-db06-4e1d-8b4f-a13f91e83208","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/fcb0de6e-db06-4e1d-8b4f-a13f91e83208","pdf_url":"https://vbn.aau.dk/ws/files/337063832/On_Loss_Functions_for_Supervised_Monaural_Time_Domain_Speech_Enhancement.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kolb\u00e6k, M, Tan, Z-H, Jensen, S H & Jensen, J 2020, 'On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, 8966946, pp. 825-838. https://doi.org/10.1109/TASLP.2020.2968738","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.01019","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.01019","pdf_url":"https://arxiv.org/pdf/1909.01019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W189850294","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1893876709","https://openalex.org/W1963970749","https://openalex.org/W2014365762","https://openalex.org/W2020307986","https://openalex.org/W2041645947","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2085191029","https://openalex.org/W2094461119","https://openalex.org/W2135284480","https://openalex.org/W2141998673","https://openalex.org/W2289394825","https://openalex.org/W2364134690","https://openalex.org/W2403117493","https://openalex.org/W2516001803","https://openalex.org/W2527611302","https://openalex.org/W2550397165","https://openalex.org/W2558539285","https://openalex.org/W2599571402","https://openalex.org/W2622055663","https://openalex.org/W2734774145","https://openalex.org/W2765425905","https://openalex.org/W2793389773","https://openalex.org/W2886515811","https://openalex.org/W2889258820","https://openalex.org/W2889286744","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2898446161","https://openalex.org/W2920977479","https://openalex.org/W2937484199","https://openalex.org/W2937525188","https://openalex.org/W2939397531","https://openalex.org/W2940177920","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2962970934","https://openalex.org/W2963045393","https://openalex.org/W2963317762","https://openalex.org/W2963351212","https://openalex.org/W2963443859","https://openalex.org/W2963453742","https://openalex.org/W2963828919","https://openalex.org/W2963909702","https://openalex.org/W2963941778","https://openalex.org/W2964058413","https://openalex.org/W2972693890","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6767164110"],"related_works":[],"abstract_inverted_index":{"Many":[0],"deep":[1,67,83],"learning-based":[2,68,84],"speech":[3,24,35,46,69,85,173,191],"enhancement":[4,47,70,86,174,192],"algorithms":[5],"are":[6],"designed":[7],"to":[8],"minimize":[9],"the":[10,41,55,58,62,79,109,128],"mean-square":[11],"error":[12],"(MSE)":[13],"in":[14,127,145],"some":[15],"transform":[16],"domain":[17],"between":[18],"a":[19,22,113,155,169,182,186],"predicted":[20],"and":[21],"target":[23],"signal.":[25],"However,":[26],"optimizing":[27],"for":[28,118,190],"MSE":[29],"does":[30],"not":[31],"necessarily":[32],"guarantee":[33],"high":[34],"quality":[36],"or":[37],"intelligibility,":[38],"which":[39,122,177],"is":[40,52,112,181],"ultimate":[42],"goal":[43],"of":[44,57,65,81,171],"many":[45],"algorithms.":[48],"Additionally,":[49],"only":[50],"little":[51],"known":[53],"about":[54],"impact":[56],"loss":[59,76,94,101,156,188],"function":[60,157,189],"on":[61,159],"emerging":[63],"class":[64],"time-domain":[66,82],"systems.":[71,87,193],"We":[72],"study":[73],"how":[74],"popular":[75,172],"functions":[77,95,102],"influence":[78],"performance":[80,136,167],"First,":[88],"we":[89,106,131,152],"demonstrate":[90],"that":[91,108,133,154,179],"perceptually":[92],"inspired":[93],"might":[96],"be":[97,139],"advantageous":[98],"over":[99],"classical":[100],"like":[103],"MSE.":[104],"Furthermore,":[105],"show":[107,153],"learning":[110],"rate":[111],"crucial":[114],"design":[115],"parameter":[116],"even":[117],"adaptive":[119],"gradient-based":[120],"optimizers,":[121],"has":[123],"been":[124],"generally":[125],"overlooked":[126],"literature.":[129],"Also,":[130],"found":[132],"waveform":[134],"matching":[135],"metrics":[137],"must":[138],"used":[140],"with":[141],"caution":[142],"as":[143,185],"they":[144],"certain":[146],"situations":[147],"can":[148],"fail":[149],"completely.":[150],"Finally,":[151],"based":[158],"scale-invariant":[160],"signal-to-distortion":[161],"ratio":[162],"(SI-SDR)":[163],"achieves":[164],"good":[165,183],"general":[166],"across":[168],"range":[170],"evaluation":[175],"metrics,":[176],"suggests":[178],"SI-SDR":[180],"candidate":[184],"general-purpose":[187]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":17}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-09-12T00:00:00"}