{"id":"https://openalex.org/W4409763559","doi":"https://doi.org/10.1109/taslpro.2025.3564118","title":"Progressive Residual Extraction Based Pre-Training for Speech Representation Learning","display_name":"Progressive Residual Extraction Based Pre-Training for Speech Representation Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409763559","doi":"https://doi.org/10.1109/taslpro.2025.3564118"},"language":"en","primary_location":{"id":"doi:10.1109/taslpro.2025.3564118","doi":"https://doi.org/10.1109/taslpro.2025.3564118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslpro.2025.3564118","pdf_url":null,"source":{"id":"https://openalex.org/S5407042752","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"2998-4173","issn":["2998-4173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.00387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106558173","display_name":"Tianrui Wang","orcid":"https://orcid.org/0000-0002-2765-5889","observed_orcids":["https://orcid.org/0000-0002-2765-5889"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2765-5889","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146848038","display_name":"Jin Li","orcid":"https://orcid.org/0009-0009-8021-6023","observed_orcids":["https://orcid.org/0009-0009-8021-6023"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-8021-6023","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262","observed_orcids":["https://orcid.org/0000-0002-8195-3262"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748272","display_name":"Rui Cao","orcid":"https://orcid.org/0000-0003-4906-0453","observed_orcids":["https://orcid.org/0000-0003-4906-0453"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Cao","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X","observed_orcids":["https://orcid.org/0000-0001-7423-617X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7423-617X","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105269944","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861","observed_orcids":["https://orcid.org/0000-0002-8094-6861"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8094-6861","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529","observed_orcids":["https://orcid.org/0000-0003-2017-4529"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["Saw Swee Hock School of Public Health, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2017-4529","affiliations":[{"raw_affiliation_string":"Saw Swee Hock School of Public Health, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015888","display_name":"Xiaobao Wang","orcid":"https://orcid.org/0000-0001-5086-4964","observed_orcids":["https://orcid.org/0000-0001-5086-4964"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5086-4964","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070236689","display_name":"Yu Guang Wang","orcid":"https://orcid.org/0000-0002-7450-0273","observed_orcids":["https://orcid.org/0000-0002-7450-0273"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuguang Wang","raw_affiliation_strings":["Huiyan Technology (Tianjin) Company Ltd., Tianjin, China","Huiyan Technology (Tianjin) Co., Ltd., Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huiyan Technology (Tianjin) Company Ltd., Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"Huiyan Technology (Tianjin) Co., Ltd., Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821","observed_orcids":["https://orcid.org/0000-0002-9237-4821"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-9237-4821","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Guangdong, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003140157","display_name":"Nyima Tashi","orcid":"https://orcid.org/0000-0003-4826-9052","observed_orcids":["https://orcid.org/0000-0003-4826-9052"]},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nyima Tashi","raw_affiliation_strings":["School of Information Science and Technology, Tibet University, Lhasa, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Tibet University, Lhasa, China","institution_ids":["https://openalex.org/I140786321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.8052,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72077403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"33","issue":null,"first_page":"1825","last_page":"1837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9839000105857849,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9839000105857849,"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/T10860","display_name":"Speech and Audio Processing","score":0.013100000098347664,"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":0.0012000000569969416,"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/self-supervised-speech-representation-learning","display_name":"self-supervised speech representation learning","score":0.8059999942779541},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5630000233650208},{"id":"https://openalex.org/keywords/pitch-variability","display_name":"pitch variation","score":0.597000002861023},{"id":"https://openalex.org/keywords/speaker-information","display_name":"speaker information","score":0.8140000104904175},{"id":"https://openalex.org/keywords/hubert","display_name":"HuBERT","score":0.8500000238418579},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.722000002861023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9779999852180481},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.968999981880188},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.9990000128746033},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742703914642334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6931493282318115},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.633906364440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5494815111160278},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5113961100578308},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4518139958381653},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44094809889793396},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41714394092559814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4165528118610382},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3805444538593292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3434692621231079},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33634084463119507},{"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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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":3,"locations":[{"id":"doi:10.1109/taslpro.2025.3564118","doi":"https://doi.org/10.1109/taslpro.2025.3564118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslpro.2025.3564118","pdf_url":null,"source":{"id":"https://openalex.org/S5407042752","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"2998-4173","issn":["2998-4173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-3"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2409.00387","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.00387","pdf_url":"https://arxiv.org/pdf/2409.00387","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.00387","doi":"https://doi.org/10.48550/arxiv.2409.00387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.00387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.00387","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.00387","pdf_url":"https://arxiv.org/pdf/2409.00387","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2883670753","display_name":null,"funder_award_id":"U23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409763559.pdf","grobid_xml":"https://content.openalex.org/works/W4409763559.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1574447377","https://openalex.org/W2041086022","https://openalex.org/W2131738223","https://openalex.org/W2146334809","https://openalex.org/W2396366106","https://openalex.org/W2580662672","https://openalex.org/W2726515241","https://openalex.org/W2900368655","https://openalex.org/W2939710050","https://openalex.org/W2972943112","https://openalex.org/W2982223350","https://openalex.org/W3020570669","https://openalex.org/W3024869864","https://openalex.org/W3034021666","https://openalex.org/W3035725276","https://openalex.org/W3041561163","https://openalex.org/W3082130377","https://openalex.org/W3095410713","https://openalex.org/W3108792608","https://openalex.org/W3169320628","https://openalex.org/W3178321840","https://openalex.org/W3179803166","https://openalex.org/W3197580070","https://openalex.org/W3197659778","https://openalex.org/W3203407300","https://openalex.org/W3206252155","https://openalex.org/W3207300132","https://openalex.org/W3209984917","https://openalex.org/W4224933800","https://openalex.org/W4225939199","https://openalex.org/W4226312351","https://openalex.org/W4232282348","https://openalex.org/W4250024550","https://openalex.org/W4283659485","https://openalex.org/W4285144981","https://openalex.org/W4287660544","https://openalex.org/W4307323391","https://openalex.org/W4311724836","https://openalex.org/W4366147765","https://openalex.org/W4366824201","https://openalex.org/W4372340947","https://openalex.org/W4375869164","https://openalex.org/W4376653535","https://openalex.org/W4385478165","https://openalex.org/W4385822740","https://openalex.org/W4392904157","https://openalex.org/W4392969497","https://openalex.org/W4393863141","https://openalex.org/W4394862910","https://openalex.org/W4401070302","https://openalex.org/W4409019657","https://openalex.org/W6780218876","https://openalex.org/W6862144568","https://openalex.org/W7133185223","https://openalex.org/W7133212238"],"related_works":["https://openalex.org/W4401597866","https://openalex.org/W4392903066","https://openalex.org/W4404295211","https://openalex.org/W4306169301","https://openalex.org/W7164983113","https://openalex.org/W4385823298","https://openalex.org/W4226403810","https://openalex.org/W4319586675","https://openalex.org/W4415797743","https://openalex.org/W4283659485"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,93,118],"(SSL)":[2],"has":[3],"garnered":[4],"significant":[5,37,174],"attention":[6],"in":[7,12,115],"speech":[8,17,34,126,153,184,188],"processing,":[9],"particularly":[10],"excelling":[11],"linguistic":[13],"tasks":[14],"such":[15,180],"as":[16,105,181],"recognition.":[18],"However,":[19],"improving":[20],"the":[21,81,84,92,102,112,122,143],"performance":[22,175],"of":[23,33,94,124],"pre-trained":[24],"models":[25],"across":[26,177],"various":[27,166],"downstream":[28,167],"tasks\u2014each":[29],"requiring":[30],"distinct":[31],"types":[32],"information\u2014remains":[35],"a":[36,44],"challenge.":[38],"To":[39],"address":[40],"this,":[41],"we":[42,53,97,132],"propose":[43],"progressive":[45],"residual":[46,99],"extraction":[47],"based":[48],"SSL":[49,63,195],"method,":[50],"namedPROGRE.":[51],"Specifically,":[52],"introduce":[54],"two":[55],"lightweight,":[56],"specialized":[57],"task":[58],"modules":[59,114],"into":[60],"an":[61],"encoder-style":[62],"backbone":[64],"to":[65,69,79,110,161],"enhance":[66],"its":[67],"ability":[68],"extract":[70,135],"pitch":[71,86,136],"variation":[72,87],"and":[73,88,91,139,190,200],"speaker":[74,89,182],"information":[75,90,120],"from":[76,142],"speech.":[77,145],"Furthermore,":[78],"mitigate":[80],"incompatibility":[82],"between":[83],"reinforced":[85],"content":[95,140],"information,":[96,154],"employ":[98],"extraction,":[100],"leveraging":[101],"extracted":[103],"representations":[104,141,164],"references":[106],"or":[107],"conditioning":[108],"signals":[109],"guide":[111],"subsequent":[113],"more":[116],"effectively":[117],"content-related":[119],"under":[121],"supervision":[123],"HuBERT-based":[125],"masking":[127],"prediction.":[128],"In":[129],"this":[130],"manner,":[131],"can":[133],"incrementally":[134],"variation,":[137],"speaker,":[138],"input":[144],"Finally,":[146],"these":[147],"multiple":[148],"representations,":[149],"each":[150],"capturing":[151],"diverse":[152],"are":[155],"combined":[156],"using":[157],"different":[158],"layer":[159],"weights":[160],"produce":[162],"task-specific":[163],"for":[165],"tasks.":[168],"Experimental":[169],"results":[170],"demonstrate":[171],"that":[172],"ourPROGREachieves":[173],"improvements":[176],"several":[178],"tasks,":[179],"identification,":[183],"recognition,":[185,187],"emotion":[186],"enhancement,":[189],"voice":[191],"conversion,":[192],"outperforming":[193],"excellent":[194],"methods":[196],"like":[197],"wav2vec2.0,":[198],"HuBERT,":[199],"WavLM.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2025-04-25T00:00:00"}