{"id":"https://openalex.org/W2566925314","doi":"https://doi.org/10.1109/taslp.2016.2639323","title":"Collaborative Joint Training With Multitask Recurrent Model for Speech and Speaker Recognition","display_name":"Collaborative Joint Training With Multitask Recurrent Model for Speech and Speaker Recognition","publication_year":2016,"publication_date":"2016-12-13","ids":{"openalex":"https://openalex.org/W2566925314","doi":"https://doi.org/10.1109/taslp.2016.2639323","mag":"2566925314"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2639323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2639323","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, Beijing, China","Chengdu Institute of Computer Applications, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Chengdu Institute of Computer Applications, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology and the Center for Speech and Language Technologies, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology and the Center for Speech and Language Technologies, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology and the Center for Speech and Language Technologies, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology and the Center for Speech and Language Technologies, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069973475","display_name":"Ravichander Vipperla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ravichander Vipperla","raw_affiliation_strings":["Nuance, Marlow, U.K"],"affiliations":[{"raw_affiliation_string":"Nuance, Marlow, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056437232"],"corresponding_institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":10.2834,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.98218633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"3","first_page":"493","last_page":"504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.9972000122070312,"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":0.778075635433197},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6860164403915405},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6814221143722534},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6674067974090576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6552862524986267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5104712247848511},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5079935193061829},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5050893425941467},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3906690180301666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858482539653778},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3626197874546051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778075635433197},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6860164403915405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6814221143722534},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6674067974090576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6552862524986267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5104712247848511},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5079935193061829},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5050893425941467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3906690180301666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858482539653778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3626197874546051},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2639323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2639323","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1598214476","display_name":null,"funder_award_id":"61633013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G465702083","display_name":null,"funder_award_id":"2013CB329302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G803898012","display_name":null,"funder_award_id":"61371136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8204283577","display_name":null,"funder_award_id":"61271389","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1542418153","https://openalex.org/W1593899551","https://openalex.org/W1779452081","https://openalex.org/W1971914237","https://openalex.org/W1978660892","https://openalex.org/W1985371235","https://openalex.org/W1993660824","https://openalex.org/W1994606281","https://openalex.org/W2006046472","https://openalex.org/W2020344439","https://openalex.org/W2021193063","https://openalex.org/W2025198378","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2055452932","https://openalex.org/W2069281977","https://openalex.org/W2078169166","https://openalex.org/W2079623482","https://openalex.org/W2085373612","https://openalex.org/W2089883580","https://openalex.org/W2100495367","https://openalex.org/W2102113734","https://openalex.org/W2107638917","https://openalex.org/W2110798204","https://openalex.org/W2114925438","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2169860302","https://openalex.org/W2183016404","https://openalex.org/W2186517251","https://openalex.org/W2286443923","https://openalex.org/W2293634267","https://openalex.org/W2295582178","https://openalex.org/W2401812832","https://openalex.org/W2406778302","https://openalex.org/W2616180702","https://openalex.org/W2913340405","https://openalex.org/W2962711229","https://openalex.org/W2962751625","https://openalex.org/W2963068250","https://openalex.org/W2963522845","https://openalex.org/W2964243145","https://openalex.org/W4205286048","https://openalex.org/W4206285905","https://openalex.org/W4246559809","https://openalex.org/W4254983205","https://openalex.org/W4297797495","https://openalex.org/W6631362777","https://openalex.org/W6632318365","https://openalex.org/W6635395492","https://openalex.org/W6635641079","https://openalex.org/W6638005537","https://openalex.org/W6640764786","https://openalex.org/W6675365184","https://openalex.org/W6676481782","https://openalex.org/W6686491854","https://openalex.org/W6686850381","https://openalex.org/W6695606915","https://openalex.org/W6696934422","https://openalex.org/W6697274609","https://openalex.org/W6712730384","https://openalex.org/W6713287686"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,31,92,116],"and":[2,12,25,81,93,117,135],"speaker":[3,27,94,118],"recognition":[4,119],"are":[5,13],"traditionally":[6],"treated":[7],"as":[8,121],"two":[9],"independent":[10],"tasks":[11,80,120],"studied":[14],"separately.":[15],"The":[16,126],"human":[17],"brain":[18],"in":[19,32,43],"contrast":[20],"deciphers":[21],"the":[22,26,30,40,61,69,85,104,136],"linguistic":[23],"content,":[24],"traits":[28],"from":[29],"a":[33,74,97],"collaborative":[34,47,79,131],"manner.":[35],"This":[36,72],"key":[37],"observation":[38],"motivates":[39],"work":[41],"presented":[42],"this":[44],"paper.":[45],"A":[46],"joint":[48,88],"training":[49,140],"approach":[50],"based":[51],"on":[52,113],"multitask":[53,105,130],"recurrent":[54,106],"neural":[55,107],"network":[56],"models":[57,109],"is":[58,66,73,101,133,142],"proposed,":[59],"where":[60],"output":[62],"of":[63,87,90,128,138],"one":[64],"task":[65],"backpropagated":[67],"to":[68,123],"other":[70],"tasks.":[71],"general":[75],"framework":[76],"for":[77],"learning":[78,89,132],"fits":[82],"well":[83],"with":[84],"goal":[86],"automatic":[91,115],"recognition.":[95],"Through":[96],"comprehensive":[98],"study,":[99],"it":[100],"shown":[102],"that":[103],"net":[108],"deliver":[110],"improved":[111],"performance":[112],"both":[114],"compared":[122],"single-task":[124],"systems.":[125],"strength":[127],"such":[129],"analyzed,":[134],"impact":[137],"various":[139],"configurations":[141],"investigated.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}