{"id":"https://openalex.org/W3162863443","doi":"https://doi.org/10.1109/icassp39728.2021.9413900","title":"Time-Domain Loss Modulation Based on Overlap Ratio for Monaural Conversational Speaker Separation","display_name":"Time-Domain Loss Modulation Based on Overlap Ratio for Monaural Conversational Speaker Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162863443","doi":"https://doi.org/10.1109/icassp39728.2021.9413900","mag":"3162863443"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan Taherian","raw_affiliation_strings":["The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA","The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5744","last_page":"5748"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.837837815284729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407059073448181},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6009888052940369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5926739573478699},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46508094668388367},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4592978060245514},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42237573862075806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39305055141448975},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19331133365631104}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.837837815284729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407059073448181},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6009888052940369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5926739573478699},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46508094668388367},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4592978060245514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42237573862075806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39305055141448975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19331133365631104},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1767093935","https://openalex.org/W2291877678","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2760103357","https://openalex.org/W2792764867","https://openalex.org/W2803322398","https://openalex.org/W2808631503","https://openalex.org/W2888954542","https://openalex.org/W2889503488","https://openalex.org/W2952218014","https://openalex.org/W2962788625","https://openalex.org/W2962866211","https://openalex.org/W2963351448","https://openalex.org/W2972460025","https://openalex.org/W2991403827","https://openalex.org/W2996969697","https://openalex.org/W3008283340","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015390914","https://openalex.org/W3016232124","https://openalex.org/W3016912202","https://openalex.org/W3099330747","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W6749825310","https://openalex.org/W6773628751","https://openalex.org/W6774687970","https://openalex.org/W6782142667"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W2401567014"],"abstract_inverted_index":{"Existing":[0],"speaker":[1,67],"separation":[2,43,68],"methods":[3,15],"deliver":[4],"excellent":[5],"performance":[6,44],"on":[7,70,106,114],"fully":[8],"overlapped":[9,28,88],"signal":[10],"mixtures.":[11],"To":[12],"apply":[13],"these":[14],"in":[16,32],"daily":[17],"conversations":[18],"that":[19,74,121],"include":[20],"occasional":[21],"concurrent":[22],"speakers,":[23],"recent":[24],"studies":[25],"incorporate":[26],"both":[27],"and":[29],"non-overlapped":[30,49],"segments":[31,50,93],"the":[33,42,52,55,58,79,92,99,102,115],"training":[34,38,73],"data.":[35],"However,":[36],"such":[37],"data":[39],"can":[40],"degrade":[41],"due":[45],"to":[46,57,130],"triviality":[47],"of":[48,101],"where":[51],"model":[53],"reflects":[54],"input":[56],"output.":[59],"We":[60,97],"propose":[61],"a":[62],"new":[63,84],"loss":[64,85,104],"function":[65,86,105],"for":[66],"based":[69],"permutation":[71],"invariant":[72],"dynamically":[75],"reweighs":[76],"losses":[77],"using":[78],"segment":[80],"overlap":[81],"ratio.":[82],"The":[83],"emphasizes":[87],"regions":[89],"while":[90],"deemphasizing":[91],"with":[94],"single":[95],"speakers.":[96],"demonstrate":[98],"effectiveness":[100],"proposed":[103,123],"an":[107],"automatic":[108],"speech":[109],"recognition":[110],"(ASR)":[111],"task.":[112],"Experiments":[113],"recently":[116],"introduced":[117],"LibriCSS":[118],"corpus":[119],"show":[120],"our":[122],"single-channel":[124],"method":[125],"produces":[126],"consistent":[127],"improvements":[128],"compared":[129],"baseline":[131],"methods.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}