{"id":"https://openalex.org/W4372267354","doi":"https://doi.org/10.1109/icassp49357.2023.10096066","title":"Streaming Voice Conversion via Intermediate Bottleneck Features and Non-Streaming Teacher Guidance","display_name":"Streaming Voice Conversion via Intermediate Bottleneck Features and Non-Streaming Teacher Guidance","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267354","doi":"https://doi.org/10.1109/icassp49357.2023.10096066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5055175414","display_name":"Yuanzhe Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuanzhe Chen","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334100","display_name":"Ming Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Tu","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329338","display_name":"Tang Li","orcid":"https://orcid.org/0000-0003-0123-1364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang Li","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353869","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-4510-2436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119011914","display_name":"Jiaxin Li","orcid":"https://orcid.org/0000-0002-8594-0506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxin Li","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106698700","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-8075-1784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichao Wang","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162279","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0002-4078-1273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339106","display_name":"Yu\u2010Ping Wang","orcid":"https://orcid.org/0000-0001-9340-5864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI), ByteDance"],"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI), ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5055175414"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0428,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80709423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9990000128746033,"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":0.7538098096847534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6852920651435852},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6464351415634155},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6357994079589844},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5514029264450073},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.508115291595459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538098096847534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6852920651435852},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6464351415634155},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6357994079589844},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5514029264450073},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.508115291595459},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/icassp49357.2023.10096066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2518172956","https://openalex.org/W2593414223","https://openalex.org/W2945478979","https://openalex.org/W3015412285","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W3109064156","https://openalex.org/W3111562797","https://openalex.org/W3156592906","https://openalex.org/W3168719651","https://openalex.org/W3193566630","https://openalex.org/W3197943112","https://openalex.org/W3198533616","https://openalex.org/W4224923642","https://openalex.org/W4225322394","https://openalex.org/W4226039367","https://openalex.org/W4283024503","https://openalex.org/W4301371414","https://openalex.org/W4395957972","https://openalex.org/W6762533536","https://openalex.org/W6777437564","https://openalex.org/W6786325012","https://openalex.org/W6787040858","https://openalex.org/W6793624898","https://openalex.org/W6803425590","https://openalex.org/W6803547063","https://openalex.org/W6838824532"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W4387098302","https://openalex.org/W2500371832","https://openalex.org/W1524071955","https://openalex.org/W169399214","https://openalex.org/W3100825170"],"abstract_inverted_index":{"Streaming":[0],"voice":[1,10],"conversion":[2],"(VC)":[3],"is":[4],"the":[5,9,40,46,57,86,100,111],"task":[6],"of":[7,11,45,56,85,120,125,131,138],"converting":[8],"one":[12],"person":[13],"to":[14,33,65,71],"another":[15],"in":[16],"real-time.":[17],"Previous":[18],"streaming":[19,50,117,145],"VC":[20,74,118,146],"methods":[21],"use":[22,66],"phonetic":[23],"posteriorgrams":[24],"(PPGs)":[25],"extracted":[26],"from":[27],"automatic":[28],"speech":[29],"recognition":[30],"(ASR)":[31],"systems":[32,75],"represent":[34],"speaker-independent":[35],"information.":[36],"However,":[37],"PPGs":[38,51],"lack":[39],"prosody":[41,81],"and":[42,49,82,110,127],"phonation":[43,83],"information":[44,84],"source":[47,58,87],"speaker,":[48],"contain":[52],"undesired":[53],"leaked":[54],"timbre":[55,101,129],"speaker.":[59,88],"In":[60],"this":[61],"paper,":[62],"we":[63,90],"propose":[64,91],"intermediate":[67],"bottleneck":[68],"features":[69],"(IBFs)":[70],"replace":[72],"PPGs.":[73],"trained":[76],"with":[77],"IBFs":[78,109],"retain":[79],"more":[80],"Furthermore,":[89],"a":[92,115,122,128,134],"non-streaming":[93],"teacher":[94],"guidance":[95],"(TG)":[96],"framework":[97,113],"that":[98,106],"addresses":[99],"leakage":[102],"problem.":[103],"Experiments":[104],"show":[105],"our":[107],"proposed":[108],"TG":[112],"achieve":[114],"state-of-the-art":[116],"naturalness":[119],"3.85,":[121],"content":[123],"consistency":[124],"3.77,":[126],"similarity":[130],"3.77":[132],"under":[133],"future":[135],"receptive":[136],"field":[137],"160":[139],"ms":[140],"which":[141],"significantly":[142],"outperform":[143],"previous":[144],"systems.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}