{"id":"https://openalex.org/W4408353473","doi":"https://doi.org/10.1109/icassp49660.2025.10888480","title":"DistillW2N: A Lightweight One-Shot Whisper to Normal Voice Conversion Model Using Distillation of Self-Supervised Features","display_name":"DistillW2N: A Lightweight One-Shot Whisper to Normal Voice Conversion Model Using Distillation of Self-Supervised Features","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353473","doi":"https://doi.org/10.1109/icassp49660.2025.10888480"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5076444953","display_name":"Tianyi Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyi Tan","raw_affiliation_strings":["Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057903680","display_name":"Haoxin Ruan","orcid":"https://orcid.org/0000-0002-7093-4613"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxin Ruan","raw_affiliation_strings":["Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103002395","display_name":"Xinan Chen","orcid":"https://orcid.org/0000-0001-9620-3264"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinan Chen","raw_affiliation_strings":["Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437965","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-4081-0687"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029938873","display_name":"Zhibin Lin","orcid":"https://orcid.org/0000-0003-3952-8147"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Lin","raw_affiliation_strings":["Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055874861","display_name":"Jing Lu","orcid":"https://orcid.org/0000-0002-8866-9926"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Lu","raw_affiliation_strings":["Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustic, Nanjing University,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076444953"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.6828,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94870347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9983000159263611,"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":0.9983000159263611,"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":0.9528999924659729,"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":0.9294000267982483,"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":0.7563688158988953},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6331931948661804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5141196846961975},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4562671184539795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44517311453819275},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07563889026641846},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05505141615867615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563688158988953},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6331931948661804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5141196846961975},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4562671184539795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44517311453819275},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07563889026641846},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05505141615867615},{"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/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/7","score":0.49000000953674316,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1502652411","https://openalex.org/W2022047569","https://openalex.org/W2516966418","https://openalex.org/W2937579788","https://openalex.org/W2946555236","https://openalex.org/W2972359262","https://openalex.org/W2972667718","https://openalex.org/W3015465870","https://openalex.org/W3081424945","https://openalex.org/W3127686677","https://openalex.org/W3161480375","https://openalex.org/W3167533889","https://openalex.org/W3203140070","https://openalex.org/W3205878676","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W3215615641","https://openalex.org/W4225956675","https://openalex.org/W4297841557","https://openalex.org/W4307475373","https://openalex.org/W4312443924","https://openalex.org/W4316494542","https://openalex.org/W4323322934","https://openalex.org/W4372260053","https://openalex.org/W4372341094","https://openalex.org/W4391021757","https://openalex.org/W4391021791","https://openalex.org/W4392902750","https://openalex.org/W4392904500","https://openalex.org/W4392909950","https://openalex.org/W4402115997","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6778823374","https://openalex.org/W6781924407","https://openalex.org/W6783867762","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6873245699","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574"],"abstract_inverted_index":{"Whisper":[0],"to":[1,50,73,128,134,152],"Normal":[2],"voice":[3],"conversion":[4],"(W2N)":[5],"holds":[6],"great":[7],"promise":[8],"for":[9,114,145],"assistive":[10],"communication":[11],"and":[12,21,43,79,91,93,110,164,169,179],"healthcare,":[13],"making":[14,47],"it":[15,48],"an":[16],"exciting":[17],"area":[18],"of":[19,66],"research":[20],"development.":[22],"Recent":[23],"advancements":[24],"in":[25,53],"W2N":[26,62],"are":[27,181],"predominantly":[28],"driven":[29],"by":[30,83,105],"self-supervised":[31],"speech":[32,90,117],"representation":[33],"learning":[34],"(SSL)":[35],"techniques.":[36],"While":[37],"effective,":[38],"SSL":[39,154],"requires":[40],"extensive":[41],"parameters":[42,163],"high":[44],"computational":[45],"costs,":[46],"impractical":[49],"be":[51],"deployed":[52],"real-world":[54],"applications.":[55],"We":[56],"propose":[57],"DistillW2N,":[58],"a":[59,67,94,131],"lightweight":[60,115],"one-shot":[61],"model.":[63],"DistillW2N":[64,140],"consists":[65],"speech-to-unit":[68],"(S2U)":[69],"encoder,":[70],"which":[71,98],"seeks":[72],"close":[74],"the":[75,123,143],"gap":[76],"between":[77],"whispered":[78],"normal":[80,89],"content":[81,100],"units":[82,101,104],"distilling":[84],"HuBERT-Soft":[85],"representations":[86],"from":[87,130],"both":[88],"pseudo-whisper,":[92],"unit-to-speech":[95],"(U2S)":[96],"decoder,":[97],"incorporates":[99],"with":[102],"timbre":[103],"Style-Adaptive":[106],"Layer":[107],"Normalization":[108],"(SALN)":[109],"leverages":[111],"SoundStream":[112],"decoder":[113],"high-quality":[116],"synthesis.":[118],"Moreover,":[119],"we":[120],"discover":[121],"that":[122,139],"S2U":[124],"encoder":[125],"is":[126],"able":[127],"learn":[129],"VAD":[132],"model":[133,158],"trim":[135],"noise.":[136],"Experiments":[137],"show":[138],"significantly":[141],"improves":[142],"intelligibility":[144],"whisper":[146],"while":[147],"preserving":[148],"speaker":[149],"similarity":[150],"compared":[151],"prevailing":[153],"approaches.":[155],"The":[156],"resulting":[157],"demands":[159],"only":[160],"10.91":[161],"M":[162],"1.63":[165],"GMACs":[166],"per":[167],"second":[168],"runs":[170],"approximately":[171],"5":[172],"times":[173],"faster":[174],"than":[175],"QuickVC.":[176],"All":[177],"samples":[178],"code":[180],"available":[182],"at":[183],"https://github.com/tan90xx/distillw2n.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}