{"id":"https://openalex.org/W3158551136","doi":"https://doi.org/10.1109/iscas51556.2021.9401372","title":"Attention-Based Multi-Task Learning for Speech-Enhancement and Speaker-Identification in Multi-Speaker Dialogue Scenario","display_name":"Attention-Based Multi-Task Learning for Speech-Enhancement and Speaker-Identification in Multi-Speaker Dialogue Scenario","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3158551136","doi":"https://doi.org/10.1109/iscas51556.2021.9401372","mag":"3158551136"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5021812640","display_name":"Chiang-Jen Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chiang-Jen Peng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073462845","display_name":"Yun-Ju Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Ju Chan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798840","display_name":"Cheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I99908691"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021812640"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59465855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.8186773061752319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7790096998214722},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6239728927612305},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5568037033081055},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5126163363456726},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5073196291923523},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4758450984954834},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.47009941935539246},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4544024169445038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4449027180671692},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4100992977619171},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17741844058036804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186773061752319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7790096998214722},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6239728927612305},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5568037033081055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5126163363456726},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5073196291923523},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4758450984954834},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.47009941935539246},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4544024169445038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4449027180671692},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4100992977619171},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17741844058036804},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas51556.2021.9401372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1968939597","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2046056978","https://openalex.org/W2101042021","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2130178255","https://openalex.org/W2130476329","https://openalex.org/W2141998673","https://openalex.org/W2150769028","https://openalex.org/W2159202424","https://openalex.org/W2163101527","https://openalex.org/W2187089797","https://openalex.org/W2379331960","https://openalex.org/W2403766732","https://openalex.org/W2405774341","https://openalex.org/W2406778302","https://openalex.org/W2527611302","https://openalex.org/W2586068394","https://openalex.org/W2594607416","https://openalex.org/W2607725416","https://openalex.org/W2624871570","https://openalex.org/W2742079690","https://openalex.org/W2755891984","https://openalex.org/W2788241093","https://openalex.org/W2890538051","https://openalex.org/W2890820256","https://openalex.org/W2890964092","https://openalex.org/W2950673314","https://openalex.org/W2963403868","https://openalex.org/W2963677766","https://openalex.org/W2964243145","https://openalex.org/W2972425344","https://openalex.org/W2972583914","https://openalex.org/W2991015288","https://openalex.org/W3016129867","https://openalex.org/W3022404557","https://openalex.org/W3087549734","https://openalex.org/W3091830790","https://openalex.org/W3147539069","https://openalex.org/W3161904430","https://openalex.org/W4253928870","https://openalex.org/W4385245566","https://openalex.org/W6639532686","https://openalex.org/W6679324631","https://openalex.org/W6713287686","https://openalex.org/W6713298849","https://openalex.org/W6733312898","https://openalex.org/W6738279954","https://openalex.org/W6739365718","https://openalex.org/W6739901393","https://openalex.org/W6742058293","https://openalex.org/W6744261651","https://openalex.org/W6754005058","https://openalex.org/W6783292247","https://openalex.org/W6784121926"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W3000153094","https://openalex.org/W1493012537","https://openalex.org/W2542062716","https://openalex.org/W2175373321","https://openalex.org/W2738829087"],"abstract_inverted_index":{"Multi-task":[0],"learning":[1,44],"(MTL)":[2],"and":[3,35,51,65,79,92,104,112,159],"attention":[4],"mechanism":[5,38],"have":[6],"been":[7],"proven":[8],"to":[9,39,88,125],"effectively":[10,155],"extract":[11],"robust":[12],"acoustic":[13],"features":[14,103,129],"for":[15,130],"various":[16],"speech-related":[17],"tasks":[18],"in":[19,110,116,142],"noisy":[20,164],"environments.":[21],"In":[22],"this":[23],"study,":[24],"we":[25],"propose":[26],"an":[27],"attention-based":[28],"MTL":[29,34],"(ATM)":[30],"approach":[31],"that":[32,46,150],"integrates":[33],"the":[36,90,101,107,134,151,167,170,179],"attention-weighting":[37],"simultaneously":[40],"realize":[41],"a":[42,74,80,162],"multi-model":[43],"structure":[45],"performs":[47],"speech":[48,108,157],"enhancement":[49],"(SE)":[50],"speaker":[52,114],"identification":[53],"(SI).":[54],"The":[55,68,95,118,146],"proposed":[56,135,152,180],"ATM":[57,97,136,181],"system":[58,98,137,153],"consists":[59],"of":[60,73,161,169],"three":[61],"parts:":[62],"SE,":[63],"SI,":[64],"attention-Net":[66],"(AttNet).":[67],"SE":[69],"part":[70],"is":[71,86],"composed":[72],"long-short-term":[75],"memory":[76],"(LSTM)":[77],"model,":[78],"deep":[81],"neural":[82],"network":[83],"(DNN)":[84],"model":[85],"used":[87],"develop":[89],"SI":[91,171],"AttNet":[93,119],"parts.":[94],"overall":[96],"first":[99],"extracts":[100],"representative":[102,128],"then":[105],"enhances":[106],"signals":[109],"LSTM-SE":[111],"specifies":[113],"identity":[115],"DNN-SI.":[117],"computes":[120],"weights":[121],"based":[122],"on":[123,138],"DNN-SI":[124],"prepare":[126],"better":[127],"LSTM-SE.":[131],"We":[132],"tested":[133],"Taiwan":[139],"Mandarin":[140],"hearing":[141],"noise":[143],"test":[144],"sentences.":[145],"evaluation":[147],"results":[148],"confirmed":[149],"can":[154,172],"enhance":[156],"quality":[158],"intelligibility":[160],"given":[163],"input.":[165],"Moreover,":[166],"accuracy":[168],"also":[173],"be":[174],"notably":[175],"improved":[176],"by":[177],"using":[178],"system.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
