{"id":"https://openalex.org/W3015915076","doi":"https://doi.org/10.1109/icassp40776.2020.9053521","title":"The Sound of My Voice: Speaker Representation Loss for Target Voice Separation","display_name":"The Sound of My Voice: Speaker Representation Loss for Target Voice Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015915076","doi":"https://doi.org/10.1109/icassp40776.2020.9053521","mag":"3015915076"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022555543","display_name":"Soyeon Choe","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyeon Choe","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021831317"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":1.6761,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84364778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7289","last_page":"7293"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994000196456909,"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/spectrogram","display_name":"Spectrogram","score":0.8404877185821533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7257291078567505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7245749831199646},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6662821769714355},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6468800902366638},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6240655779838562},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6024670600891113},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5794468522071838},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.464901328086853},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.44118037819862366},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41503798961639404},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3917806148529053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3542061746120453},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2130274772644043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08709213137626648},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06665268540382385}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8404877185821533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257291078567505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7245749831199646},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6662821769714355},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6468800902366638},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6240655779838562},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6024670600891113},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5794468522071838},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.464901328086853},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.44118037819862366},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41503798961639404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3917806148529053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3542061746120453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2130274772644043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08709213137626648},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06665268540382385},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2096733369","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2467139031","https://openalex.org/W2475287302","https://openalex.org/W2527729766","https://openalex.org/W2558580397","https://openalex.org/W2558649592","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2766465839","https://openalex.org/W2787692317","https://openalex.org/W2808631503","https://openalex.org/W2891833136","https://openalex.org/W2914217321","https://openalex.org/W2963373786","https://openalex.org/W2963522749","https://openalex.org/W2964121744","https://openalex.org/W2964238697","https://openalex.org/W2972425344","https://openalex.org/W2973016613","https://openalex.org/W2973062255","https://openalex.org/W3099206234","https://openalex.org/W6631190155","https://openalex.org/W6718379498","https://openalex.org/W6719816043","https://openalex.org/W6727697161"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2898606530","https://openalex.org/W2206035908","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333"],"abstract_inverted_index":{"Content":[0],"and":[1,31,51,85,123],"style":[2,12],"representations":[3,82],"have":[4],"been":[5],"widely":[6],"studied":[7],"in":[8],"the":[9,43,48,56,61,69,77,80,102,120,130],"field":[10],"of":[11,71,83],"transfer.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,32,124],"propose":[18,91],"a":[19],"new":[20],"loss":[21,95,132],"function":[22,133],"using":[23,119],"speaker":[24,35,45,73,81,93,104],"content":[25],"representation":[26,36,94],"for":[27],"audio":[28],"source":[29,86,116],"separation,":[30],"call":[33],"it":[34,54],"loss.":[37],"The":[38],"objective":[39],"is":[40,112],"to":[41,60,100,114,129],"extract":[42],"target":[44,72,103],"voice":[46],"from":[47,55,106],"noisy":[49],"input":[50],"also":[52,90],"remove":[53,101],"residual":[57,107],"components.":[58],"Compared":[59],"conventional":[62],"spectral":[63],"reconstruction,":[64],"our":[65],"proposed":[66],"framework":[67,111],"maximizes":[68],"use":[70],"information":[74,105],"by":[75],"minimizing":[76],"distance":[78],"between":[79],"reference":[84],"separation":[87,117],"output.":[88,109],"We":[89],"triplet":[92],"as":[96],"an":[97],"additional":[98,136],"criterion":[99],"spectrogram":[108],"VoiceFilter":[110],"adopted":[113],"evaluate":[115],"performance":[118],"VCTK":[121],"database,":[122],"achieved":[125],"improved":[126],"performances":[127],"compared":[128],"baseline":[131],"without":[134],"any":[135],"network":[137],"parameters.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}