{"id":"https://openalex.org/W4224916425","doi":"https://doi.org/10.1109/icassp43922.2022.9747590","title":"Controllable Speech Representation Learning Via Voice Conversion and AIC Loss","display_name":"Controllable Speech Representation Learning Via Voice Conversion and AIC Loss","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916425","doi":"https://doi.org/10.1109/icassp43922.2022.9747590"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747590","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5100714799","display_name":"Yunyun Wang","orcid":"https://orcid.org/0000-0002-5884-9408"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyun Wang","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"6682","last_page":"6686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.747650682926178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6973780989646912},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.6268329620361328},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5867149829864502},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5024018287658691},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4521293342113495},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4501146078109741},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43897590041160583},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.429552286863327},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4192041754722595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4186785817146301},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3587634563446045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1429855227470398},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06731292605400085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747650682926178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6973780989646912},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.6268329620361328},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5867149829864502},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5024018287658691},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4521293342113495},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4501146078109741},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43897590041160583},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.429552286863327},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4192041754722595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4186785817146301},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3587634563446045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1429855227470398},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06731292605400085},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747590","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2148228080","https://openalex.org/W2527729766","https://openalex.org/W2896457183","https://openalex.org/W2945478979","https://openalex.org/W2962788625","https://openalex.org/W2962793481","https://openalex.org/W2962866891","https://openalex.org/W2970006822","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W3002433751","https://openalex.org/W3015805741","https://openalex.org/W3034794073","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3096567388","https://openalex.org/W3096864844","https://openalex.org/W3100270690","https://openalex.org/W3100378519","https://openalex.org/W3140429000","https://openalex.org/W3160652646","https://openalex.org/W3196667132","https://openalex.org/W3209059054","https://openalex.org/W4292779060","https://openalex.org/W4297817572","https://openalex.org/W6631190155","https://openalex.org/W6727697161","https://openalex.org/W6755207826","https://openalex.org/W6755257315","https://openalex.org/W6762533536","https://openalex.org/W6767111847","https://openalex.org/W6776390925","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2556771176","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"Speech":[0],"representation":[1,26,69,75],"learning":[2,70],"transforms":[3],"speech":[4,14,68],"into":[5,79],"features":[6],"that":[7,138],"are":[8],"suitable":[9],"for":[10,41,64],"downstream":[11],"tasks,":[12,24,43],"e.g.":[13],"recognition,":[15],"phoneme":[16],"classification,":[17],"or":[18],"speaker":[19,93],"identification.":[20],"For":[21],"such":[22],"recognition":[23],"a":[25,62,80,110],"can":[27,76,97],"be":[28,51,77,98],"lossy":[29,47],"(non-invertible),":[30],"which":[31,117],"is":[32],"typical":[33],"of":[34],"BERT-like":[35],"self-supervised":[36],"models.":[37],"However,":[38],"when":[39],"used":[40],"synthesis":[42,104],"we":[44,118,136],"find":[45],"these":[46],"representations":[48],"prove":[49],"to":[50,53,84,101],"insufficient":[52],"plausibly":[54],"reconstruct":[55],"the":[56,85,103,156],"input":[57],"signal.":[58],"This":[59],"paper":[60],"introduces":[61],"method":[63],"invertible":[65],"and":[66,95,126,133],"controllable":[67],"based":[71],"on":[72],"disentanglement.":[73],"The":[74],"decoded":[78],"signal":[81],"perceptually":[82],"identical":[83],"original.":[86],"Moreover,":[87],"its":[88],"disentangled":[89,157],"components":[90],"(content,":[91],"pitch,":[92],"identity,":[94],"energy)":[96],"controlled":[99],"independently":[100],"alter":[102],"result.":[105],"Our":[106],"model":[107,114],"builds":[108],"upon":[109],"zero-shot":[111],"voice":[112,145],"conversion":[113,146],"AutoVC-F0,":[115],"in":[116,144],"introduce":[119],"alteration":[120],"invariant":[121],"content":[122],"loss":[123],"(AIC":[124],"loss)":[125],"adversarial":[127],"training":[128],"(GAN).":[129],"Through":[130],"objective":[131],"measures":[132],"subjective":[134],"tests,":[135],"show":[137],"our":[139],"formulation":[140],"offers":[141],"significant":[142],"improvement":[143],"sound":[147],"quality":[148],"as":[149,151],"well":[150],"more":[152],"precise":[153],"control":[154],"over":[155],"features.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}