{"id":"https://openalex.org/W4392910613","doi":"https://doi.org/10.1109/icassp48485.2024.10445962","title":"Zero Shot Audio To Audio Emotion Transfer With Speaker Disentanglement","display_name":"Zero Shot Audio To Audio Emotion Transfer With Speaker Disentanglement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910613","doi":"https://doi.org/10.1109/icassp48485.2024.10445962"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035530630","display_name":"Soumya Dutta","orcid":"https://orcid.org/0000-0002-3936-6718"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumya Dutta","raw_affiliation_strings":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":4.1715,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94960131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10371","last_page":"10375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9513999819755554,"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":0.9513999819755554,"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":0.6438925266265869},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5741627812385559},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5396642088890076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5378716588020325},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5369420051574707},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.46665191650390625},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3435918688774109},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.2470126748085022},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22102737426757812},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06545847654342651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438925266265869},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5741627812385559},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5396642088890076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5378716588020325},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5369420051574707},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.46665191650390625},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3435918688774109},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.2470126748085022},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22102737426757812},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06545847654342651},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1731081199","https://openalex.org/W2030931454","https://openalex.org/W2077801020","https://openalex.org/W2148846882","https://openalex.org/W2166637769","https://openalex.org/W2517513811","https://openalex.org/W2894821115","https://openalex.org/W2899361462","https://openalex.org/W2945478979","https://openalex.org/W2962750014","https://openalex.org/W2964243274","https://openalex.org/W2981087920","https://openalex.org/W3015241559","https://openalex.org/W3015707499","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3097962967","https://openalex.org/W3098557217","https://openalex.org/W3140429000","https://openalex.org/W3141523618","https://openalex.org/W3142644187","https://openalex.org/W3163573274","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W4221147462","https://openalex.org/W4226421465","https://openalex.org/W4296070378","https://openalex.org/W4366197508","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385822669","https://openalex.org/W4385823370","https://openalex.org/W6637618735","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6851555575"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1996547972","https://openalex.org/W2139941521","https://openalex.org/W2363866404","https://openalex.org/W9205999","https://openalex.org/W2392717295","https://openalex.org/W2123022792","https://openalex.org/W2494591065","https://openalex.org/W4388334345","https://openalex.org/W3110605476"],"abstract_inverted_index":{"The":[0,78,119],"problem":[1],"of":[2,12,28,51,105,143,179],"audio-to-audio":[3],"(A2A)":[4],"style":[5,10],"transfer":[6,50,177],"involves":[7],"replacing":[8],"the":[9,13,19,24,29,49,56,61,65,70,76,102,106,116,131,138,144,149,167,180],"features":[11],"source":[14,30,58,150,168],"audio":[15,21,59,67],"with":[16,60],"those":[17],"from":[18,75,137,148,166],"target":[20,66,139,170],"while":[22,68,141],"preserving":[23],"content":[25,53,74],"related":[26],"attributes":[27],"audio.":[31,151],"In":[32,152],"this":[33],"paper,":[34],"we":[35,96,155,172],"propose":[36,97],"an":[37],"efficient":[38],"approach,":[39],"termed":[40],"as":[41],"Zero-shot":[42],"Emotion":[43],"Style":[44],"Transfer":[45],"(ZEST),":[46],"that":[47,114],"allows":[48],"emotional":[52],"present":[54],"in":[55,64],"given":[57,107],"one":[62],"embedded":[63],"retaining":[69],"speaker":[71,88],"and":[72,90,110,186],"speech":[73,84,108,117],"source.":[77],"proposed":[79,181],"system":[80],"builds":[81],"upon":[82],"decomposing":[83],"into":[85],"semantic":[86],"tokens,":[87],"representations":[89],"emotion":[91,132,176],"embeddings.":[92],"Using":[93],"these":[94],"factors,":[95],"a":[98,112,124],"framework":[99],"to":[100],"reconstruct":[101],"pitch":[103],"contour":[104],"signal":[109],"train":[111],"decoder":[113],"reconstructs":[115],"signal.":[118],"model":[120,183],"is":[121,134],"trained":[122],"using":[123,160,184],"self-supervision":[125],"based":[126],"reconstruction":[127],"loss.":[128],"During":[129],"conversion,":[130],"embedding":[133],"alone":[135],"derived":[136,147],"audio,":[140,171],"rest":[142],"factors":[145],"are":[146],"our":[153],"experiments,":[154],"show":[156],"that,":[157],"even":[158],"without":[159],"parallel":[161],"training":[162],"data":[163],"or":[164,169],"labels":[165],"illustrate":[173],"zero":[174],"shot":[175],"capabilities":[178],"ZEST":[182],"objective":[185],"subjective":[187],"quality":[188],"evaluations.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}