{"id":"https://openalex.org/W4416800052","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249207","title":"ASRQ-VC: ASR-Guided Speech Content Quantization for High-Fidelity Voice Conversion","display_name":"ASRQ-VC: ASR-Guided Speech Content Quantization for High-Fidelity Voice Conversion","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800052","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249207"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5063542250","display_name":"Songlin Liu","orcid":"https://orcid.org/0000-0003-3202-5125"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Songting Liu","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deheng Ye","raw_affiliation_strings":["Tencent Inc.,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc.,Singapore","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102070404","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0001-7920-4927"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["Tencent Inc.,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc.,Singapore","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037624853","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0003-3024-1350"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17667995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"741","last_page":"746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6800000071525574,"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":0.6800000071525574,"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/T10863","display_name":"Voice and Speech Disorders","score":0.1454000025987625,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.04100000113248825,"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/speaker-recognition","display_name":"Speaker recognition","score":0.588699996471405},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4410000145435333},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.397599995136261},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3889000117778778},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.3840000033378601},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.375900000333786},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.3582000136375427},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7921000123023987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4410000145435333},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3095410713","https://openalex.org/W3140429000","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225302959","https://openalex.org/W4372260053","https://openalex.org/W4385823264","https://openalex.org/W4385823321","https://openalex.org/W4386076493","https://openalex.org/W4388979610","https://openalex.org/W4393156644"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"conversion":[1,85],"(VC)":[2],"seeks":[3],"to":[4,13,103],"transform":[5],"the":[6,19,38,60,95],"voice":[7,12,40,84],"of":[8,37,62],"a":[9,14,47,83,116,126],"source":[10,30,39,55],"speaker's":[11],"target":[15],"speaker":[16,31,56,74,122],"while":[17],"preserving":[18],"original":[20],"linguistic":[21,63,106],"content.":[22],"A":[23],"persistent":[24],"challenge":[25],"in":[26],"this":[27,78],"task":[28],"is":[29],"timbre":[32,57,127],"leakage,":[33],"where":[34],"residual":[35],"characteristics":[36],"remain":[41],"after":[42],"conversion.":[43],"Existing":[44],"methods":[45],"face":[46],"tradeoff:":[48],"using":[49],"narrow":[50],"bottleneck":[51],"features":[52],"often":[53],"removes":[54],"but":[58,71],"at":[59],"expense":[61],"fidelity,":[64],"whereas":[65],"wide":[66],"bottlenecks":[67],"preserve":[68],"more":[69],"content":[70,107],"risk":[72],"retaining":[73],"traits.":[75],"To":[76],"address":[77],"trade-off,":[79],"we":[80],"propose":[81],"ASRQ-VC,":[82],"framework":[86],"that":[87],"integrates":[88],"automatic":[89],"speech":[90],"recognition":[91],"(ASR)":[92],"loss":[93],"into":[94],"VQ-VAE":[96],"encoder":[97,128],"with":[98,121],"finite":[99],"scalar":[100],"quantization":[101],"(FSQ)":[102],"enforce":[104],"speaker-invariant":[105],"representations.":[108],"These":[109],"discrete":[110],"representations":[111],"are":[112,164],"then":[113],"utilized":[114],"within":[115],"VITS-based":[117],"synthesis":[118],"architecture":[119],"enhanced":[120],"verification":[123],"embeddings":[124],"and":[125,136,146,158],"for":[129],"fine-grained":[130],"identity":[131],"modeling.":[132],"Experiments":[133],"on":[134,166],"LibriTTS":[135],"VCTK":[137],"datasets":[138],"show":[139],"state-of-the-art":[140],"performance,":[141],"achieving":[142],"11.2":[143],"%":[144,157,160],"WER":[145],"0.460":[147],"SECS,":[148],"surpassing":[149],"prior":[150],"SOTA":[151],"method":[152],"by":[153],"absolute":[154],"value":[155],"2.6":[156],"2.7":[159],"respectively.":[161],"Audio":[162],"samples":[163],"available":[165],"https://asq-vc.github.io/":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}