{"id":"https://openalex.org/W4387010434","doi":"https://doi.org/10.1109/taslp.2023.3317568","title":"Disentangled Adversarial Domain Adaptation for Phonation Mode Detection in Singing and Speech","display_name":"Disentangled Adversarial Domain Adaptation for Phonation Mode Detection in Singing and Speech","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387010434","doi":"https://doi.org/10.1109/taslp.2023.3317568"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3317568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3317568","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/A5100328543","display_name":"Yixin Wang","orcid":"https://orcid.org/0000-0002-7330-801X"},"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"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yixin Wang","raw_affiliation_strings":["Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China","School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7330-801X","affiliations":[{"raw_affiliation_string":"Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323695","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-2197-7035"},"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":"Wei Wei","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2197-7035","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042584368","display_name":"Xiangming Gu","orcid":"https://orcid.org/0000-0003-0637-8664"},"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":"Xiangming Gu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0637-8664","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"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":"Xiaohong Guan","raw_affiliation_strings":["MOE KLINNS Laboratory Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China","Center for Intelligent and Networked Systems, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8826-0362","affiliations":[{"raw_affiliation_string":"MOE KLINNS Laboratory Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Center for Intelligent and Networked Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"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"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China","School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0123-1260","affiliations":[{"raw_affiliation_string":"Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8699,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73384764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"3746","last_page":"3759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.9516997337341309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7164826989173889},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6461859345436096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.637164831161499},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45246338844299316},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4443740248680115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4404025077819824},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.41760149598121643},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17998990416526794},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17996740341186523},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.13436341285705566},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06959125399589539}],"concepts":[{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.9516997337341309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7164826989173889},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6461859345436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.637164831161499},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45246338844299316},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4443740248680115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4404025077819824},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.41760149598121643},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17998990416526794},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17996740341186523},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.13436341285705566},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06959125399589539},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3317568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3317568","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":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4208651041","display_name":null,"funder_award_id":"T2341003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5552192335","display_name":null,"funder_award_id":"R-252-000-A56-114","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W30609886","https://openalex.org/W276227194","https://openalex.org/W1483501585","https://openalex.org/W1522301498","https://openalex.org/W1545150940","https://openalex.org/W1731081199","https://openalex.org/W1882958252","https://openalex.org/W1970747557","https://openalex.org/W1971243715","https://openalex.org/W1982254271","https://openalex.org/W1987280716","https://openalex.org/W2001257796","https://openalex.org/W2021107069","https://openalex.org/W2024590593","https://openalex.org/W2029874859","https://openalex.org/W2044505491","https://openalex.org/W2050006267","https://openalex.org/W2051457717","https://openalex.org/W2067709094","https://openalex.org/W2081345242","https://openalex.org/W2095176743","https://openalex.org/W2099773255","https://openalex.org/W2109020278","https://openalex.org/W2109138290","https://openalex.org/W2115846934","https://openalex.org/W2153903782","https://openalex.org/W2157177661","https://openalex.org/W2159291411","https://openalex.org/W2161632835","https://openalex.org/W2170505850","https://openalex.org/W2295471129","https://openalex.org/W2407685581","https://openalex.org/W2408239454","https://openalex.org/W2508726376","https://openalex.org/W2770890514","https://openalex.org/W2795155917","https://openalex.org/W2803832867","https://openalex.org/W2888473984","https://openalex.org/W2889017834","https://openalex.org/W2889118666","https://openalex.org/W2889378348","https://openalex.org/W2962866891","https://openalex.org/W2963495494","https://openalex.org/W3008479202","https://openalex.org/W3015469592","https://openalex.org/W3035762612","https://openalex.org/W3038083940","https://openalex.org/W3084380363","https://openalex.org/W3109093849","https://openalex.org/W3163829335","https://openalex.org/W3167533889","https://openalex.org/W3200345197","https://openalex.org/W3217778739","https://openalex.org/W4221146826","https://openalex.org/W4285231507","https://openalex.org/W4295312788","https://openalex.org/W4307934381","https://openalex.org/W4375869266","https://openalex.org/W6628860550","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6639480849","https://openalex.org/W6683633756","https://openalex.org/W6714030504","https://openalex.org/W6750109254","https://openalex.org/W6752051073","https://openalex.org/W6766978945","https://openalex.org/W6801059870","https://openalex.org/W6846452521","https://openalex.org/W6911743356"],"related_works":["https://openalex.org/W1987047733","https://openalex.org/W2989774764","https://openalex.org/W2390529913","https://openalex.org/W1914697324","https://openalex.org/W2167212246","https://openalex.org/W2027982229","https://openalex.org/W3013996185","https://openalex.org/W2142368101","https://openalex.org/W4253972549","https://openalex.org/W4393733332"],"abstract_inverted_index":{"Phonation":[0],"mode":[1,56,79,91,109,206],"detection":[2,57],"predicts":[3],"phonation":[4,55,78,90,108,205],"modes":[5],"and":[6,12,20,36,86,98,110,119,144,152,157,211,221,228],"their":[7],"temporal":[8],"boundaries":[9],"in":[10,142,224],"singing":[11,151,156,168,210],"speech,":[13,153,174],"holding":[14],"promise":[15],"for":[16,89,150],"characterizing":[17],"voice":[18,225],"quality":[19,226],"vocal":[21],"health.":[22],"However,":[23],"it":[24],"is":[25,137,213],"very":[26],"challenging":[27],"due":[28],"to":[29,73,173,215],"the":[30,54,60,63,70,74,96,99,117,129,134,148,182,198,204],"domain":[31,49,72,76,124,159],"disparities":[32],"between":[33],"training":[34],"data":[35,169],"unannotated":[37],"real-world":[38],"recordings.":[39],"To":[40],"tackle":[41],"this":[42],"problem,":[43],"we":[44,93,201],"develop":[45],"a":[46,164,188],"disentangled":[47,199],"adversarial":[48,123],"adaptation":[50,160],"network,":[51],"which":[52],"adapts":[53],"model":[58,165,189],"with":[59,181],"structure":[61],"of":[62,121,147,178,184],"convolutional":[64],"recurrent":[65],"neural":[66],"network":[67],"pre-trained":[68],"on":[69,82,167,192],"source":[71],"target":[75],"without":[77],"labels.":[80],"Based":[81],"our":[83,113],"curated":[84],"sung":[85],"spoken":[87],"dataset":[88],"detection,":[92],"demonstrate":[94],"that":[95,128,163,203],"subject":[97,135],"singing-speech":[100],"mismatches":[101],"cause":[102],"performance":[103,130],"decline.":[104],"By":[105,195],"disentangling":[106],"domain-invariant":[107],"domain-specific":[111],"embeddings,":[112,200],"method":[114],"greatly":[115],"enhances":[116],"effectiveness":[118],"explainability":[120],"unsupervised":[122],"adaptation.":[125],"Experiments":[126],"show":[127],"drop":[131],"caused":[132],"by":[133,209],"mismatch":[136],"alleviated":[138],"via":[139],"adaptation,":[140],"resulting":[141],"44.7%":[143],"6.8%":[145],"improvement":[146],"F-score":[149,177,183],"respectively.":[154],"The":[155],"speech":[158,193,212],"experiment":[161],"indicates":[162],"trained":[166,191],"can":[170],"be":[171],"adapted":[172],"yielding":[175],"an":[176],"0.56,":[179],"commensurate":[180],"0.59":[185],"achieved":[186],"using":[187],"exclusively":[190],"data.":[194],"further":[196],"investigating":[197],"find":[202],"feature":[207],"shared":[208],"invariant":[214],"pitch.":[216],"These":[217],"results":[218],"inspire":[219],"reliable":[220],"versatile":[222],"applications":[223],"evaluation":[227],"paralinguistic":[229],"information":[230],"retrieval.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}