{"id":"https://openalex.org/W4385823370","doi":"https://doi.org/10.21437/interspeech.2023-39","title":"Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion","display_name":"Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823370","doi":"https://doi.org/10.21437/interspeech.2023-39"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.17508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077845043","display_name":"Yun Chen","orcid":"https://orcid.org/0000-0001-6819-6562"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054786043","display_name":"Lingxiao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxiao Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109407767","display_name":"Qi Chen","orcid":"https://orcid.org/0009-0002-9490-618X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034685928","display_name":"Jianhuang Lai","orcid":"https://orcid.org/0000-0003-3883-2024"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-Huang Lai","raw_affiliation_strings":["Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China","Guangdong Province Key Laboratory of Information Security Technology, China","School of Computer Science and Engineering, Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"Guangdong Province Key Laboratory of Information Security Technology, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018298892","display_name":"Xiaohua Xie","orcid":"https://orcid.org/0000-0002-0310-4679"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohua Xie","raw_affiliation_strings":["Guangdong Province Key Laboratory of Information Security Technology, China","Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China","School of Computer Science and Engineering, Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Key Laboratory of Information Security Technology, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018298892"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.8987,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79177838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2068","last_page":"2072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9973000288009644,"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":0.8080722093582153},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5640304684638977},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5174072980880737},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4805070161819458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42505043745040894},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42487427592277527},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4227231740951538},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4120247960090637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3299664855003357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080722093582153},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5640304684638977},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5174072980880737},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4805070161819458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42505043745040894},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42487427592277527},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4227231740951538},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4120247960090637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3299664855003357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.17508","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.17508","pdf_url":"https://arxiv.org/pdf/2312.17508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2312.17508","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.17508","pdf_url":"https://arxiv.org/pdf/2312.17508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823370.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2295107390","https://openalex.org/W2331128040","https://openalex.org/W2885005742","https://openalex.org/W2899361462","https://openalex.org/W2938833595","https://openalex.org/W2945478979","https://openalex.org/W3008691130","https://openalex.org/W3015699566","https://openalex.org/W3015719316","https://openalex.org/W3025680351","https://openalex.org/W3092028330","https://openalex.org/W3095169545","https://openalex.org/W3095930733","https://openalex.org/W3096939667","https://openalex.org/W3163573274","https://openalex.org/W3196667132","https://openalex.org/W3214606349","https://openalex.org/W4205742757","https://openalex.org/W4213469706","https://openalex.org/W4221147462","https://openalex.org/W4224926192","https://openalex.org/W4287250434","https://openalex.org/W4297914850","https://openalex.org/W4312680544","https://openalex.org/W4312881655","https://openalex.org/W4313065316"],"related_works":["https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4380370144","https://openalex.org/W2009950829","https://openalex.org/W4386232293","https://openalex.org/W2382178633"],"abstract_inverted_index":{"Emotional":[0],"Voice":[1],"Conversion":[2],"aims":[3],"to":[4,9,49,60,68,79],"manipulate":[5],"a":[6,10,46,84],"speech":[7,97],"according":[8],"given":[11],"emotion":[12,63,71,94],"while":[13],"preserving":[14],"non-emotion":[15],"components.":[16],"Existing":[17],"approaches":[18],"cannot":[19],"well":[20],"express":[21],"fine-grained":[22,62,93],"emotional":[23,39],"attributes.":[24],"In":[25,74],"this":[26],"paper,":[27],"we":[28,77],"propose":[29,78],"an":[30],"Attention-based":[31],"Interactive":[32],"diseNtangling":[33],"Network":[34],"(AINN)":[35],"that":[36,102],"leverages":[37],"instance-wise":[38],"knowledge":[40],"for":[41],"voice":[42],"conversion.":[43],"We":[44],"introduce":[45],"two-stage":[47],"pipeline":[48],"effectively":[50],"train":[51],"our":[52,103],"network:":[53],"Stage":[54,75],"I":[55],"utilizes":[56],"inter-speech":[57],"contrastive":[58],"learning":[59,67],"model":[61],"and":[64,72,95,110],"intra-speech":[65],"disentanglement":[66],"better":[69],"separate":[70],"content.":[73,98],"II,":[76],"regularize":[80],"the":[81],"conversion":[82],"with":[83],"multi-view":[85],"consistency":[86],"mechanism.":[87],"This":[88],"technique":[89],"helps":[90],"us":[91],"transfer":[92],"maintain":[96],"Extensive":[99],"experiments":[100],"show":[101],"AINN":[104],"outperforms":[105],"state-of-the-arts":[106],"in":[107],"both":[108],"objective":[109],"subjective":[111],"metrics.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}