{"id":"https://openalex.org/W4402980268","doi":"https://doi.org/10.1109/icme57554.2024.10687477","title":"Jointly Recognizing Speech and Singing Voices Based on Multi-Task Audio Source Separation","display_name":"Jointly Recognizing Speech and Singing Voices Based on Multi-Task Audio Source Separation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980268","doi":"https://doi.org/10.1109/icme57554.2024.10687477"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100624455","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5533-6909"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Bai","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050682332","display_name":"Chenxing Li","orcid":"https://orcid.org/0000-0002-3997-8212"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348588","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-4019-3420"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080620053","display_name":"Yuanyuan Zhao","orcid":"https://orcid.org/0000-0002-0196-7673"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.973800003528595,"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":0.973800003528595,"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":0.9621000289916992,"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":0.7885055541992188},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7087827920913696},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7035884857177734},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6812455058097839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6768913269042969},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3395373225212097},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13497096300125122},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07991981506347656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885055541992188},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7087827920913696},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7035884857177734},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6812455058097839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6768913269042969},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3395373225212097},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13497096300125122},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07991981506347656},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2296073425","https://openalex.org/W2734774145","https://openalex.org/W2800664709","https://openalex.org/W2890244912","https://openalex.org/W2952218014","https://openalex.org/W2962894366","https://openalex.org/W2963242190","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2973071600","https://openalex.org/W3010689477","https://openalex.org/W3013139777","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3017474798","https://openalex.org/W3097777922","https://openalex.org/W3109079702","https://openalex.org/W3197478142","https://openalex.org/W3200955206","https://openalex.org/W3205879560","https://openalex.org/W3211278025","https://openalex.org/W4210493250","https://openalex.org/W4225292962","https://openalex.org/W4285345683","https://openalex.org/W4285819380","https://openalex.org/W4296069118","https://openalex.org/W4319862721","https://openalex.org/W4384160435","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6773772901"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"In":[0],"short":[1],"video":[2],"and":[3,9,14,24,34,56,70,107],"live":[4],"broadcasts,":[5],"speech,":[6],"singing":[7,57,71],"voice,":[8],"background":[10,76],"music":[11,35],"often":[12],"overlap":[13],"obscure":[15],"each":[16,120],"other.":[17],"This":[18,38],"complexity":[19],"creates":[20],"difficulties":[21],"in":[22],"structuring":[23],"recognizing":[25],"the":[26,60,64,92,99,123],"audio":[27,43,66],"content,":[28],"which":[29,52],"may":[30],"impair":[31],"subsequent":[32],"ASR":[33,48],"understanding":[36],"applications.":[37],"paper":[39],"proposes":[40],"a":[41,102],"multi-task":[42],"source":[44],"separation":[45],"(MTASS)":[46],"based":[47],"model":[49],"called":[50],"JRSV,":[51],"Jointly":[53],"Recognizes":[54],"Speech":[55],"Voices.":[58],"Specifically,":[59],"MTASS":[61],"module":[62,82],"separates":[63],"mixed":[65,124],"into":[67],"distinct":[68],"speech":[69],"voice":[72],"tracks":[73],"while":[74],"removing":[75],"music.":[77],"The":[78],"CTC/attention":[79],"hybrid":[80],"recognition":[81,95,117],"recognizes":[83],"both":[84],"tracks.":[85],"Online":[86],"distillation":[87],"is":[88,105],"proposed":[89,100],"to":[90],"improve":[91,116],"robustness":[93],"of":[94,122],"further.":[96],"To":[97],"evaluate":[98],"methods,":[101],"benchmark":[103],"dataset":[104],"constructed":[106],"released.":[108],"Experimental":[109],"results":[110],"demonstrate":[111],"that":[112],"JRSV":[113],"can":[114],"significantly":[115],"accuracy":[118],"on":[119],"track":[121],"audio.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
