{"id":"https://openalex.org/W3198112783","doi":"https://doi.org/10.21437/interspeech.2021-858","title":"Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation","display_name":"Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198112783","doi":"https://doi.org/10.21437/interspeech.2021-858","mag":"3198112783"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-858","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","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/A5079958194","display_name":"Fan-Lin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Fan-Lin Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan","Department of Electrical Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066130866","display_name":"Yuhuai Peng","orcid":"https://orcid.org/0000-0001-9343-5377"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Huai Peng","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079958194"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.3047,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54293442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3061","last_page":"3065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T12206","display_name":"Vibration and Dynamic Analysis","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9726999998092651,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735688328742981},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7170517444610596},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6120778322219849},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6116389036178589},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5557556748390198},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5534722805023193},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3198915123939514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08861759305000305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735688328742981},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7170517444610596},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6120778322219849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6116389036178589},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5557556748390198},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5534722805023193},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3198915123939514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08861759305000305},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-858","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2031647436","https://openalex.org/W2143169494","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2760103357","https://openalex.org/W2782360754","https://openalex.org/W2890964092","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963443859","https://openalex.org/W2972460025","https://openalex.org/W2973062255","https://openalex.org/W3015199127","https://openalex.org/W3035268204","https://openalex.org/W3094831814","https://openalex.org/W3095082129","https://openalex.org/W3096796823","https://openalex.org/W3096893582","https://openalex.org/W3103434036","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W4287632494"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2287611352","https://openalex.org/W2021161555","https://openalex.org/W320684304","https://openalex.org/W4385464961","https://openalex.org/W2060903012","https://openalex.org/W2369669030","https://openalex.org/W2383458001"],"abstract_inverted_index":{"Speech":[0],"separation":[1,62,66,78,90],"has":[2],"been":[3],"extensively":[4],"studied":[5],"to":[6,35,39,63,96,114],"deal":[7],"with":[8],"the":[9,58,73,77,80,84,87,89,93,98,104,119],"cocktail":[10],"party":[11],"problem":[12,120],"in":[13],"recent":[14],"years.All":[15],"related":[16],"approaches":[17],"can":[18],"be":[19],"divided":[20],"into":[21],"two":[22,71],"categories:":[23],"time-frequency":[24],"domain":[25,29],"methods":[26,33],"and":[27,76],"time":[28],"methods.In":[30],"addition,":[31],"some":[32],"try":[34],"generate":[36],"speaker":[37,74,81],"vectors":[38],"support":[40],"source":[41],"separation.In":[42],"this":[43],"study,":[44],"we":[45],"propose":[46],"a":[47],"new":[48],"model":[49,55],"called":[50],"dualpath":[51],"filter":[52],"network":[53],"(DPFN).Our":[54],"focuses":[56],"on":[57,108],"postprocessing":[59],"of":[60,70,86,100,121],"speech":[61,65],"improve":[64],"performance.DPFN":[67],"is":[68,110],"composed":[69],"parts:":[72],"module":[75,82,91],"module.First,":[79],"infers":[83],"identities":[85],"speakers.Then,":[88],"uses":[92],"speakers'":[94],"information":[95],"extract":[97],"voices":[99],"individual":[101],"speakers":[102],"from":[103],"mixture.DPFN":[105],"constructed":[106],"based":[107],"DPRNN-TasNet":[109],"not":[111],"only":[112],"superior":[113],"DPRNN-TasNet,":[115],"but":[116],"also":[117],"avoids":[118],"permutation-invariant":[122],"training":[123],"(PIT).":[124]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}