{"id":"https://openalex.org/W4225939199","doi":"https://doi.org/10.1109/icassp43922.2022.9747763","title":"SpeechSplit2.0: Unsupervised Speech Disentanglement for Voice Conversion without Tuning Autoencoder Bottlenecks","display_name":"SpeechSplit2.0: Unsupervised Speech Disentanglement for Voice Conversion without Tuning Autoencoder Bottlenecks","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225939199","doi":"https://doi.org/10.1109/icassp43922.2022.9747763"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747763","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":"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/A5002899884","display_name":"Chak Ho Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chak Ho Chan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030425371","display_name":"Kaizhi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaizhi Qian","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354683","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-4170-4798"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002899884"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.2624,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93453832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6332","last_page":"6336"},"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":0.9958999752998352,"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/autoencoder","display_name":"Autoencoder","score":0.8286240100860596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7910114526748657},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7677792906761169},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7230187058448792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6682562232017517},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.422384113073349},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4206979274749756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3878868520259857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35357293486595154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18314266204833984}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8286240100860596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910114526748657},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7677792906761169},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7230187058448792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6682562232017517},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.422384113073349},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4206979274749756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3878868520259857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35357293486595154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18314266204833984},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747763","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":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2099621636","https://openalex.org/W2471520273","https://openalex.org/W2532494225","https://openalex.org/W2902070858","https://openalex.org/W2907262790","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2962689740","https://openalex.org/W2962793481","https://openalex.org/W2963767194","https://openalex.org/W2963830550","https://openalex.org/W2972667718","https://openalex.org/W3015805741","https://openalex.org/W3034794073","https://openalex.org/W3095123370","https://openalex.org/W3097290232","https://openalex.org/W3142644187","https://openalex.org/W3169739675","https://openalex.org/W3198605397","https://openalex.org/W6675409298","https://openalex.org/W6762533536","https://openalex.org/W6776390925","https://openalex.org/W6785164032","https://openalex.org/W6796577156"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2127970246","https://openalex.org/W3131327266","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745"],"abstract_inverted_index":{"SpeechSplit":[0,23,76],"can":[1,32],"perform":[2],"aspect-specific":[3],"voice":[4],"conversion":[5],"by":[6],"disentangling":[7],"speech":[8,49,78],"into":[9],"content,":[10],"rhythm,":[11],"pitch,":[12],"and":[13,35,80],"timbre":[14],"using":[15,58],"multiple":[16],"autoencoders":[17],"in":[18,77],"an":[19],"unsupervised":[20],"manner.":[21],"However,":[22],"requires":[24],"careful":[25],"tuning":[26],"of":[27,47,64],"the":[28,44,48,55,84],"autoencoder":[29,56],"bottlenecks,":[30],"which":[31,42],"be":[33,52],"time-consuming":[34],"less":[36],"robust.":[37],"This":[38],"paper":[39],"proposes":[40],"SpeechSplit2.0,":[41],"constrains":[43],"information":[45],"flow":[46],"component":[50],"to":[51,75,83],"disentangled":[53],"on":[54],"input":[57],"efficient":[59],"signal":[60],"processing":[61],"methods":[62],"instead":[63],"bottleneck":[65,85],"tuning.":[66],"Evaluation":[67],"results":[68],"show":[69],"that":[70],"SpeechSplit2.0":[71],"achieves":[72],"comparable":[73],"performance":[74],"disentanglement":[79],"superior":[81],"robustness":[82],"size":[86],"variations.":[87],"Our":[88],"code":[89],"is":[90],"available":[91],"at":[92],"https://github.com/biggytruck/SpeechSplit2.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-05T07:30:30.508283","created_date":"2025-10-10T00:00:00"}