{"id":"https://openalex.org/W2901702433","doi":"https://doi.org/10.1109/icassp.2019.8682790","title":"On Training Targets and Objective Functions for Deep-learning-based Audio-visual Speech Enhancement","display_name":"On Training Targets and Objective Functions for Deep-learning-based Audio-visual Speech Enhancement","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2901702433","doi":"https://doi.org/10.1109/icassp.2019.8682790","mag":"2901702433"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.06234","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063187524","display_name":"Daniel Michelsanti","orcid":"https://orcid.org/0000-0002-3575-1600"},"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":"Daniel Michelsanti","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua 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, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002081827","display_name":"Sigur\u00f0ur Sigur\u00f0sson","orcid":"https://orcid.org/0000-0001-5439-3389"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sigurdur Sigurdsson","raw_affiliation_strings":["Oticon A/S, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"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, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8077","last_page":"8081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9979000091552734,"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":0.9961000084877014,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8304978609085083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081796169281006},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7172985672950745},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5216003656387329},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5020058155059814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.491326242685318},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46451038122177124},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42276132106781006},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3636457920074463},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10476011037826538},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09304076433181763}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8304978609085083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081796169281006},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7172985672950745},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5216003656387329},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5020058155059814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491326242685318},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46451038122177124},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42276132106781006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3636457920074463},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10476011037826538},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09304076433181763},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.06234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06234","pdf_url":"https://arxiv.org/pdf/1811.06234","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/6b38ad10-b481-4001-ac61-b1f1ba460274","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85068964525&partnerID=8YFLogxK","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/6b38ad10-b481-4001-ac61-b1f1ba460274","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/6b38ad10-b481-4001-ac61-b1f1ba460274","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.06234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06234","pdf_url":"https://arxiv.org/pdf/1811.06234","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":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2010318909","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2043843997","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2101042021","https://openalex.org/W2103869314","https://openalex.org/W2106714211","https://openalex.org/W2118877769","https://openalex.org/W2121973264","https://openalex.org/W2130103520","https://openalex.org/W2137400100","https://openalex.org/W2145310550","https://openalex.org/W2164598857","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2516001803","https://openalex.org/W2586068394","https://openalex.org/W2605589342","https://openalex.org/W2765425905","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2963453742","https://openalex.org/W2964171275","https://openalex.org/W3040777582","https://openalex.org/W3123318516","https://openalex.org/W3147539069","https://openalex.org/W4232336823","https://openalex.org/W4253928870","https://openalex.org/W4289665794","https://openalex.org/W6639824700","https://openalex.org/W6677548441","https://openalex.org/W6679388247","https://openalex.org/W6713658392","https://openalex.org/W6780413204"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,9,121,142],"enhancement":[2],"(AV-SE)":[3],"is":[4,71,78],"the":[5,34,44,47,50,56,61,74,79,106,114,126,131],"task":[6,36],"of":[7,46,63,86,89,119,140],"improving":[8],"quality":[10,62,122],"and":[11,19,55,92,123],"intelligibility":[12],"in":[13,37,117,138],"a":[14,23,38,87,98,111],"noisy":[15],"environment":[16],"using":[17],"audio":[18],"visual":[20],"information":[21],"from":[22],"talker.":[24],"Recently,":[25],"deep":[26],"learning":[27],"techniques":[28],"have":[29],"been":[30],"adopted":[31],"to":[32,52,66,96],"solve":[33],"AV-SE":[35,100],"supervised":[39],"manner.":[40],"In":[41],"this":[42,64],"context,":[43],"choice":[45],"target,":[48],"i.e.":[49],"quantity":[51],"be":[53,67],"estimated,":[54],"objective":[57,93],"function,":[58],"which":[59],"quantifies":[60],"estimate,":[65],"used":[68,95],"for":[69,73],"training":[70],"critical":[72],"performance.":[75],"This":[76],"work":[77],"first":[80],"that":[81,105,108,128],"presents":[82],"an":[83],"experimental":[84],"study":[85],"range":[88],"different":[90],"targets":[91],"functions":[94],"train":[97],"deep-learning-based":[99],"system.":[101],"The":[102],"results":[103],"show":[104],"approaches":[107],"directly":[109,129],"estimate":[110],"mask":[112],"perform":[113],"best":[115],"overall":[116],"terms":[118,139],"estimated":[120,141],"intelligibility,":[124],"although":[125],"model":[127],"estimates":[130],"log":[132],"magnitude":[133],"spectrum":[134],"performs":[135],"as":[136],"good":[137],"quality.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
