{"id":"https://openalex.org/W2964243145","doi":"https://doi.org/10.1109/apsipa.2016.7820893","title":"Multi-task recurrent model for speech and speaker recognition","display_name":"Multi-task recurrent model for speech and speaker recognition","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2964243145","doi":"https://doi.org/10.1109/apsipa.2016.7820893","mag":"2964243145"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2016.7820893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"},"type":"preprint","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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":["Chengdu \u00cdnstitute of Computer Applications, Chinese Academy of Sciences","Division of Technical Innovation and Development, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Chengdu \u00cdnstitute of Computer Applications, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["Division of Technical Innovation and Development, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","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":["Division of Technical Innovation and Development, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056437232"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.22815319,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9738414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.7994348406791687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7796303629875183},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7538419961929321},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7107577323913574},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4771106541156769},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4740702211856842},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4702264964580536},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4636000692844391},{"id":"https://openalex.org/keywords/decipher","display_name":"DECIPHER","score":0.418793261051178},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.411475270986557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070136547088623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994348406791687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7796303629875183},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7538419961929321},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7107577323913574},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4771106541156769},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4740702211856842},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4702264964580536},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4636000692844391},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.418793261051178},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.411475270986557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070136547088623},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2016.7820893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1542418153","https://openalex.org/W1762484328","https://openalex.org/W1985371235","https://openalex.org/W2025198378","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2102113734","https://openalex.org/W2114925438","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2183016404","https://openalex.org/W2293634267","https://openalex.org/W2401812832","https://openalex.org/W2406778302","https://openalex.org/W2962751625","https://openalex.org/W2963522845","https://openalex.org/W2980141581","https://openalex.org/W4234330420","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6675365184","https://openalex.org/W6677390740","https://openalex.org/W6696934422","https://openalex.org/W6712730384","https://openalex.org/W6713287686"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Although":[0],"highly":[1],"correlated,":[2],"speech":[3,31,48],"and":[4,14,33,49,53],"speaker":[5,34,50],"recognition":[6,51],"have":[7],"been":[8],"regarded":[9],"as":[10],"two":[11,17,97],"independent":[12],"tasks":[13],"studied":[15],"by":[16],"communities.":[18],"This":[19,40],"is":[20,57,70],"certainly":[21],"not":[22],"the":[23,37,65,73,76,87,91,96],"way":[24],"that":[25,86],"people":[26],"behave:":[27],"we":[28],"decipher":[29],"both":[30,95],"content":[32],"traits":[35],"at":[36],"same":[38],"time.":[39],"paper":[41],"presents":[42],"a":[43,60,80],"unified":[44,61],"model":[45,56,89],"to":[46,72,79],"perform":[47],"simultaneously":[52],"altogether.":[54],"The":[55],"based":[58],"on":[59,94],"neural":[62],"network":[63],"where":[64],"output":[66],"of":[67,75],"one":[68],"task":[69],"fed":[71],"input":[74],"other,":[77],"leading":[78],"multi-task":[81],"recurrent":[82],"network.":[83],"Experiments":[84],"show":[85],"joint":[88],"outperforms":[90],"task-specific":[92],"models":[93],"tasks.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}