{"id":"https://openalex.org/W3015212100","doi":"https://doi.org/10.1109/icassp40776.2020.9054591","title":"Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis","display_name":"Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015212100","doi":"https://doi.org/10.1109/icassp40776.2020.9054591","mag":"3015212100"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5062098630","display_name":"Ting-Yao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ting-Yao Hu","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002740493","display_name":"Ashish Shrivastava","orcid":"https://orcid.org/0000-0002-2465-0708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Shrivastava","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028613002","display_name":"Oncel Tuzel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oncel Tuzel","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110720542","display_name":"Chandra Dhir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandra Dhir","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062098630"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.1814,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93152624,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3267","last_page":"3271"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9987000226974487,"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":0.7939891815185547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6051114797592163},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5283516049385071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47387051582336426},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4623137414455414},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4395887553691864},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.43041151762008667},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4184873402118683},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4134826958179474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313504457473755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10660025477409363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939891815185547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6051114797592163},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5283516049385071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47387051582336426},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4623137414455414},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4395887553691864},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.43041151762008667},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4184873402118683},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4134826958179474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313504457473755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10660025477409363},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2099471712","https://openalex.org/W2120847449","https://openalex.org/W2127141656","https://openalex.org/W2136144249","https://openalex.org/W2475287302","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2621350877","https://openalex.org/W2766812927","https://openalex.org/W2794490148","https://openalex.org/W2803832867","https://openalex.org/W2898741639","https://openalex.org/W2903739847","https://openalex.org/W2948211236","https://openalex.org/W2949382160","https://openalex.org/W2963226019","https://openalex.org/W2963272440","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2964222296","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W4232613155","https://openalex.org/W4289383906","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6718140377","https://openalex.org/W6739139180","https://openalex.org/W6739901393","https://openalex.org/W6741121127","https://openalex.org/W6745697700","https://openalex.org/W6750489868","https://openalex.org/W6752051073","https://openalex.org/W6755300632","https://openalex.org/W6755592152","https://openalex.org/W6763100362","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2466816617","https://openalex.org/W1970834875","https://openalex.org/W842936808","https://openalex.org/W3174028392","https://openalex.org/W2000517284","https://openalex.org/W2365318811","https://openalex.org/W2136503713","https://openalex.org/W2375330620","https://openalex.org/W2363755581","https://openalex.org/W2378091429"],"abstract_inverted_index":{"We":[0,124,154],"present":[1],"a":[2,11,18,54,70],"method":[3,157,171],"to":[4,56,93,126,173],"generate":[5,41],"speech":[6,20,42,104,181,199],"from":[7,17,46],"input":[8,63,91,122,176],"text":[9,92],"and":[10,52,86,138,146,192],"style":[12,28,45,59,77,145],"vector":[13,60],"that":[14],"is":[15,34,172],"extracted":[16],"reference":[19,103],"signal":[21],"in":[22,68,178],"an":[23,150],"unsupervised":[24,37,198],"manner,":[25],"i.e.,":[26],"no":[27],"annotation,":[29],"such":[30,69],"as":[31,129],"speaker":[32],"information,":[33],"required.":[35],"Existing":[36],"methods,":[38],"during":[39],"training,":[40],"by":[43,135,186],"computing":[44],"the":[47,58,62,66,76,83,90,95,102,108,111,118,121,140,144,147,170,175,179,187],"corresponding":[48],"ground":[49],"truth":[50],"sample":[51],"use":[53,82],"decoder":[55,80],"combine":[57],"with":[61],"text.":[64,123],"Training":[65],"model":[67],"way":[71],"leaks":[72],"content":[73,85,109,119,148,177],"information":[74,142],"into":[75],"vector.":[78],"The":[79,166],"can":[81],"leaked":[84],"ignore":[87],"some":[88],"of":[89,117,120,169],"minimize":[94],"reconstruction":[96],"loss.":[97],"At":[98],"inference":[99],"time,":[100],"when":[101],"does":[105],"not":[106,114],"match":[107],"input,":[110],"output":[112],"may":[113],"contain":[115],"all":[116],"refer":[125],"this":[127],"problem":[128],"\"content":[130],"leakage\",":[131],"which":[132,183],"we":[133,184],"address":[134],"explicitly":[136],"estimating":[137],"minimizing":[139],"mutual":[141],"between":[143],"through":[149],"adversarial":[151],"training":[152],"formulation.":[153],"call":[155],"our":[156],"MIST":[158],"-":[159],"Mutual":[160],"Information":[161],"based":[162],"Style":[163],"Content":[164],"Separation.":[165],"main":[167],"goal":[168],"preserve":[174],"synthesized":[180],"signal,":[182],"measure":[185],"word":[188],"error":[189],"rate":[190],"(WER)":[191],"show":[193],"substantial":[194],"improvements":[195],"over":[196],"state-of-the-art":[197],"synthesis":[200],"methods.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}