{"id":"https://openalex.org/W4385822773","doi":"https://doi.org/10.21437/interspeech.2023-191","title":"Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion","display_name":"Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822773","doi":"https://doi.org/10.21437/interspeech.2023-191"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-191","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/2309.07586","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041024295","display_name":"Suhita Ghosh","orcid":"https://orcid.org/0000-0002-5553-585X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Suhita Ghosh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205617","display_name":"Arnab Das","orcid":"https://orcid.org/0000-0001-9715-1435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnab Das","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089816799","display_name":"Yamini Sinha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamini Sinha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033995312","display_name":"Ingo Siegert","orcid":"https://orcid.org/0000-0001-7447-7141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingo Siegert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034570279","display_name":"Tim Polzehl","orcid":"https://orcid.org/0000-0001-9592-0296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Polzehl","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034558147","display_name":"Sebastian Stober","orcid":"https://orcid.org/0000-0002-1717-4133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Stober","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041024295"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5214,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71601184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2093","last_page":"2097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9934999942779541,"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":0.9934999942779541,"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":0.9854000210762024,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9557999968528748,"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":0.7418159246444702},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.721096932888031},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6060235500335693},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6040652990341187},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6024019718170166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5746920108795166},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.48105812072753906},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4683726727962494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3852520287036896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3269243836402893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418159246444702},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.721096932888031},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6060235500335693},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6040652990341187},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6024019718170166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5746920108795166},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.48105812072753906},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4683726727962494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3852520287036896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3269243836402893},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-191","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:2309.07586","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07586","pdf_url":"https://arxiv.org/pdf/2309.07586","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.07586","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07586","pdf_url":"https://arxiv.org/pdf/2309.07586","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822773.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391307871","https://openalex.org/W4392502551","https://openalex.org/W2336827033","https://openalex.org/W2505228240","https://openalex.org/W4319430321","https://openalex.org/W3047499479","https://openalex.org/W4389296211","https://openalex.org/W2922915988","https://openalex.org/W2787157782","https://openalex.org/W1876223856"],"abstract_inverted_index":{"Speech":[0],"anonymisation":[1,34],"prevents":[2],"misuse":[3],"of":[4],"spoken":[5],"data":[6],"by":[7],"removing":[8],"any":[9],"personal":[10],"identifier":[11],"while":[12],"preserving":[13],"at":[14],"least":[15],"linguistic":[16],"content.":[17],"However,":[18],"emotion":[19,61,73,78,91],"preservation":[20,92],"is":[21,100],"crucial":[22],"for":[23],"natural":[24],"human-computer":[25],"interaction.":[26],"The":[27],"well-known":[28],"voice":[29],"conversion":[30],"technique":[31],"StarGANv2-VC":[32,46],"achieves":[33],"but":[35],"fails":[36],"to":[37,67,75],"preserve":[38],"emotion.":[39,68],"This":[40,97],"work":[41],"presents":[42],"an":[43,72],"any-to-many":[44],"semi-supervised":[45],"variant":[47],"trained":[48],"on":[49,59],"partially":[50],"emotion-labelled":[51],"non-parallel":[52],"data.":[53],"We":[54],"propose":[55],"emotion-aware":[56],"losses":[57],"computed":[58],"the":[60,86,94],"embeddings":[62],"and":[63,81,108,114],"acoustic":[64],"features":[65],"correlated":[66],"Additionally,":[69],"we":[70],"use":[71],"classifier":[74],"provide":[76],"direct":[77],"supervision.":[79],"Objective":[80],"subjective":[82],"evaluations":[83],"show":[84],"that":[85],"proposed":[87],"approach":[88],"significantly":[89],"improves":[90],"over":[93,102],"vanilla":[95],"StarGANv2-VC.":[96],"considerable":[98],"improvement":[99],"seen":[101],"diverse":[103],"datasets,":[104],"emotions,":[105],"target":[106],"speakers,":[107],"inter-group":[109],"conversions":[110],"without":[111],"compromising":[112],"intelligibility":[113],"anonymisation.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}