{"id":"https://openalex.org/W3197419327","doi":"https://doi.org/10.21437/interspeech.2021-763","title":"Stabilizing Label Assignment for Speech Separation by Self-Supervised Pre-Training","display_name":"Stabilizing Label Assignment for Speech Separation by Self-Supervised Pre-Training","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197419327","doi":"https://doi.org/10.21437/interspeech.2021-763","mag":"3197419327"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-763","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-763","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/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sung-Feng Huang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028930617","display_name":"Shun-Po Chuang","orcid":"https://orcid.org/0000-0003-0720-2732"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shun-Po Chuang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084868332","display_name":"Da-Rong Liu","orcid":"https://orcid.org/0009-0005-0090-7408"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Rong Liu","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450914","display_name":"Yi\u2010Chen Chen","orcid":"https://orcid.org/0000-0002-4616-2115"},"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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chen Chen","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085238281","display_name":"Gene-Ping Yang","orcid":"https://orcid.org/0000-0002-3786-3251"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gene-Ping Yang","raw_affiliation_strings":["University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"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"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040508737"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79317106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3056","last_page":"3060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9977999925613403,"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":0.9549999833106995,"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/computer-science","display_name":"Computer science","score":0.7258805632591248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5796929597854614},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5667797327041626},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5358058214187622},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46308666467666626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4334900379180908},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30864793062210083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258805632591248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5796929597854614},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5667797327041626},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5358058214187622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46308666467666626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4334900379180908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30864793062210083},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-763","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-763","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316499","display_name":"National Applied Research Laboratories","ror":"https://ror.org/05wcstg80"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1597158214","https://openalex.org/W2031647436","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2735663686","https://openalex.org/W2896457183","https://openalex.org/W2944828972","https://openalex.org/W2948012107","https://openalex.org/W2952218014","https://openalex.org/W2962739339","https://openalex.org/W2963571336","https://openalex.org/W2972541922","https://openalex.org/W2972864514","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W3005680577","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3096893582","https://openalex.org/W3100859887","https://openalex.org/W3160903688","https://openalex.org/W4287632494","https://openalex.org/W4288088464","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2071676784","https://openalex.org/W2997094352","https://openalex.org/W4292513318","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Speech":[0],"separation":[1,56,67],"has":[2],"been":[3],"well":[4],"developed,":[5],"with":[6],"the":[7,16,49,54],"very":[8,75],"successful":[9],"permutation":[10],"invariant":[11],"training":[12,24,53],"(PIT)":[13],"approach,":[14],"although":[15],"frequent":[17],"label":[18,50],"assignment":[19,51],"switching":[20],"happening":[21],"during":[22],"PIT":[23],"remains":[25],"to":[26,43,47],"be":[27],"a":[28,81],"problem":[29],"when":[30],"better":[31],"convergence":[32],"speed":[33],"and":[34,69],"achievable":[35,79],"performance":[36],"are":[37,78],"desired.In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"perform":[44],"self-supervised":[45,62,83],"pre-training":[46],"stabilize":[48],"in":[52],"speech":[55,66],"model.Experiments":[57],"over":[58],"several":[59,64],"types":[60],"of":[61],"approaches,":[63],"typical":[65],"models":[68],"two":[70],"different":[71],"datasets":[72],"showed":[73],"that":[74],"good":[76],"improvements":[77],"if":[80],"proper":[82],"approach":[84],"is":[85],"chosen.":[86]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}