{"id":"https://openalex.org/W7148348289","doi":"https://doi.org/10.1109/asru65441.2025.11434701","title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","display_name":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148348289","doi":"https://doi.org/10.1109/asru65441.2025.11434701"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132800131","display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Zhejiang University,Computer Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Computer Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132809351","display_name":"Baotong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baotong Tian","raw_affiliation_strings":["University of Rochester,Electrical and Computer Engineering,Rochester,USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Electrical and Computer Engineering,Rochester,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094900151","display_name":"Zhiyao Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Electrical and Computer Engineering,Rochester,USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Electrical and Computer Engineering,Rochester,USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132800131"],"corresponding_institution_ids":["https://openalex.org/I168879160","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8734354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.565500020980835,"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":0.565500020980835,"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":0.10369999706745148,"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/T10860","display_name":"Speech and Audio Processing","score":0.065700002014637,"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/encoder","display_name":"Encoder","score":0.6182000041007996},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.46389999985694885},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3598000109195709},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35100001096725464},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.3474999964237213},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3452000021934509},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3208000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935000061988831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6265000104904175},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49059998989105225},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38100001215934753},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2983306500","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Voice communication","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2518172956","https://openalex.org/W2535388113","https://openalex.org/W2593414223","https://openalex.org/W2972359262","https://openalex.org/W3083423753","https://openalex.org/W3095199334","https://openalex.org/W3150572638","https://openalex.org/W3162390194","https://openalex.org/W3162517041","https://openalex.org/W3196667132","https://openalex.org/W3197659778","https://openalex.org/W3198104520","https://openalex.org/W3198575134","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4224923642","https://openalex.org/W4296068989","https://openalex.org/W4372267354","https://openalex.org/W4385823021","https://openalex.org/W4385823240","https://openalex.org/W4386132131","https://openalex.org/W4390872598","https://openalex.org/W4392909950","https://openalex.org/W4392910523","https://openalex.org/W4393160753","https://openalex.org/W4402671538","https://openalex.org/W4404783513","https://openalex.org/W4406461813","https://openalex.org/W4412888141","https://openalex.org/W4415799264","https://openalex.org/W4416035881","https://openalex.org/W6922118369","https://openalex.org/W7133196924","https://openalex.org/W7133222967"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"online":[1,44],"voice":[2,46],"conversion":[3,47],"(VC)":[4],"holds":[5],"significant":[6],"promise":[7],"for":[8,77,95],"real-time":[9,23],"communications":[10],"and":[11,28,124],"entertainment.":[12],"However,":[13],"current":[14],"VC":[15],"models":[16,121],"struggle":[17],"to":[18,31],"preserve":[19],"semantic":[20],"fidelity":[21],"under":[22],"constraints,":[24],"deliver":[25],"natural-sounding":[26],"conversions,":[27],"adapt":[29],"effectively":[30],"unseen":[32],"speaker":[33,59],"characteristics.":[34],"To":[35],"address":[36],"these":[37],"challenges,":[38],"we":[39],"introduce":[40],"Conan,":[41],"a":[42,70,100,106,111],"chunkwise":[43],"zero-shot":[45],"model":[48],"that":[49,74,87,104,117],"preserves":[50],"the":[51,54,58],"content":[52,80],"of":[53,61],"source":[55],"while":[56],"matching":[57],"representation":[60],"reference":[62,93],"speech.":[63],"Conan":[64,118],"comprises":[65],"three":[66],"core":[67],"components:":[68],"1)":[69],"Stream":[71],"Content":[72],"Extractor":[73],"leverages":[75],"Emformer":[76],"low-latency":[78],"streaming":[79],"encoding;":[81],"2)":[82],"an":[83],"Adaptive":[84],"Style":[85],"Encoder":[86],"extracts":[88],"fine-grained":[89],"stylistic":[90],"features":[91],"from":[92],"speech":[94],"enhanced":[96],"style":[97],"adaptation;":[98],"3)":[99],"Causal":[101],"Shuffle":[102],"Vocoder":[103],"implements":[105],"fully":[107],"causal":[108],"HiFiGAN":[109],"using":[110],"pixel-shuffle":[112],"mechanism.":[113],"Experimental":[114],"evaluations":[115],"demonstrate":[116],"outperforms":[119],"baseline":[120],"in":[122],"subjective":[123],"objective":[125],"metrics.":[126],"Audio":[127],"samples":[128],"can":[129],"be":[130],"found":[131],"at":[132],"https://aaronz345.github.io/ConanDemo.":[133]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}