{"id":"https://openalex.org/W3167513671","doi":"https://doi.org/10.21437/interspeech.2021-1341","title":"An Attribute-Aligned Strategy for Learning Speech Representation","display_name":"An Attribute-Aligned Strategy for Learning Speech Representation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3167513671","doi":"https://doi.org/10.21437/interspeech.2021-1341","mag":"3167513671"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1341","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.02810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105891449","display_name":"Yu-Lin Huang","orcid":"https://orcid.org/0000-0001-5018-8767"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Lin Huang","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan","MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026257400","display_name":"Bo-Hao Su","orcid":"https://orcid.org/0009-0001-0912-7417"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bo-Hao Su","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan","MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009791512","display_name":"Y.-W. Peter Hong","orcid":"https://orcid.org/0000-0001-7043-8276"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Y.-W. Peter Hong","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan","Institute of Communication Engineering, National Tsing Hua University, Taiwan","MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Communication Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan","Institute of Communication Engineering, National Tsing Hua University, Taiwan","MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Communication Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60113875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1179","last_page":"1183"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8095601797103882},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7975153923034668},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6737220287322998},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6323776841163635},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5537776947021484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4951860010623932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4903876781463623},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4802677631378174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45403337478637695},{"id":"https://openalex.org/keywords/information-leakage","display_name":"Information leakage","score":0.4432829022407532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36371445655822754},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24136784672737122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095601797103882},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7975153923034668},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6737220287322998},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6323776841163635},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5537776947021484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4951860010623932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4903876781463623},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4802677631378174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45403337478637695},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.4432829022407532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36371445655822754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24136784672737122},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1341","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.02810","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.02810","pdf_url":"https://arxiv.org/pdf/2106.02810","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.02810","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.02810","pdf_url":"https://arxiv.org/pdf/2106.02810","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W1959608418","https://openalex.org/W2085662862","https://openalex.org/W2095705004","https://openalex.org/W2607719644","https://openalex.org/W2742542661","https://openalex.org/W2770604845","https://openalex.org/W2808631503","https://openalex.org/W2898866157","https://openalex.org/W2916104401","https://openalex.org/W2945445411","https://openalex.org/W2948978827","https://openalex.org/W2949678053","https://openalex.org/W2950095160","https://openalex.org/W2953900859","https://openalex.org/W2962850167","https://openalex.org/W2963826681","https://openalex.org/W2964058423","https://openalex.org/W2968920814","https://openalex.org/W2995545690","https://openalex.org/W2997399314","https://openalex.org/W2997604315","https://openalex.org/W3015707499","https://openalex.org/W3045555759","https://openalex.org/W3103543904","https://openalex.org/W4288264465","https://openalex.org/W4299812321","https://openalex.org/W4310650179","https://openalex.org/W4391602018"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Advancement":[0],"in":[1],"speech":[2,18,47,68,79],"technology":[3],"has":[4],"brought":[5],"convenience":[6],"to":[7,27,45,73,108,137],"our":[8,126],"life.":[9],"However,":[10],"the":[11,15,109,123,131],"concern":[12],"is":[13],"on":[14,97,104,118],"rise":[16],"as":[17],"signal":[19],"contains":[20],"multiple":[21,139],"personal":[22],"attributes,":[23],"which":[24,66],"would":[25],"lead":[26],"either":[28],"sensitive":[29],"information":[30],"leakage":[31],"or":[32],"bias":[33],"toward":[34],"decision.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,59],"propose":[40,60],"an":[41,75,84],"attribute-aligned":[42],"learning":[43,116,128],"strategy":[44,129],"derive":[46,74],"representation":[48,69,77,86],"that":[49],"can":[50],"flexibly":[51],"address":[52],"these":[53],"issues":[54],"by":[55],"attribute-selection":[56],"mechanism.":[57],"Specifically,":[58],"a":[61,101,119],"layered-representation":[62],"variational":[63],"autoencoder":[64],"(LR-VAE),":[65],"factorizes":[67],"into":[70],"attribute-sensitive":[71],"nodes,":[72],"identity-free":[76,98],"for":[78,87],"emotion":[80,121],"recognition":[81],"(SER),":[82],"and":[83,100,133],"emotionless":[85,105],"speaker":[88],"verification":[89],"(SV).":[90],"Our":[91],"proposed":[92,127],"method":[93,112],"achieves":[94],"competitive":[95],"performances":[96],"SER":[99],"better":[102],"performance":[103],"SV,":[106],"comparing":[107],"current":[110],"state-of-the-art":[111],"of":[113],"using":[114],"adversarial":[115],"applied":[117],"large":[120],"corpora,":[122],"MSP-Podcast.":[124],"Also,":[125],"reduces":[130],"model":[132],"training":[134],"process":[135],"needed":[136],"achieve":[138],"privacy-preserving":[140],"tasks.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}