{"id":"https://openalex.org/W7166881038","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1020","title":"MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora","display_name":"MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166881038","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1020"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1020","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1020","pdf_url":"https://aclanthology.org/2026.findings-acl.1020.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1020.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139811251","display_name":"Tao Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139757056","display_name":"Yuxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735024","display_name":"Yuancheng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuancheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139734031","display_name":"Xueyao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784004","display_name":"Dekun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dekun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005342759","display_name":"Chaoren Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaoren Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133612197","display_name":"Xun Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xun Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139739699","display_name":"Zhizheng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86961379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20392","last_page":"20405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7773000001907349,"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":0.7773000001907349,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04019999876618385,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.03539999946951866,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5845000147819519},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4668999910354614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3183000087738037},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.28380000591278076},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.2596000134944916}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6431999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6237000226974487},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.445499986410141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1020","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1020","pdf_url":"https://aclanthology.org/2026.findings-acl.1020.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1020","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1020","pdf_url":"https://aclanthology.org/2026.findings-acl.1020.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4227895438671112}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166881038.pdf","grobid_xml":"https://content.openalex.org/works/W7166881038.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Voice":[0],"imitation":[1,174],"aims":[2],"to":[3,7,23,59,68,122,144,157],"transform":[4],"source":[5,32],"speech":[6,88,108,127,150],"match":[8],"a":[9,83,102,177],"reference":[10],"speaker's":[11],"timbre":[12],"and":[13,33,79,151,197],"speaking":[14],"style":[15],"while":[16,112,188],"preserving":[17],"linguistic":[18],"content.A":[19],"straightforward":[20],"approach":[21,104],"is":[22,49,89],"train":[24],"on":[25,134,165],"triplets":[26],"of":[27,148],"(source,":[28],"reference,":[29],"target),":[30],"where":[31],"target":[34,40],"share":[35],"the":[36,42,73,80,120,130,146,159],"same":[37],"content":[38],"but":[39],"matches":[41],"reference's":[43],"voice":[44,173],"characteristics,":[45],"yet":[46,179],"such":[47],"data":[48,62,136],"extremely":[50],"scarce.Existing":[51],"approaches":[52],"either":[53],"employ":[54],"carefully":[55],"designed":[56],"disentanglement":[57],"architectures":[58],"bypass":[60],"this":[61,135],"scarcity":[63],"or":[64],"leverage":[65],"external":[66],"systems":[67],"synthesize":[69],"pseudo-parallel":[70],"training":[71,92,110,164],"data.However,":[72],"former":[74],"requires":[75],"intricate":[76],"model":[77,121],"design,":[78],"latter":[81],"faces":[82],"quality":[84,132,175],"ceiling":[85],"when":[86,163],"synthetic":[87,107,131,166],"used":[90],"as":[91,109,116],"targets.To":[93],"address":[94],"these":[95],"limitations,":[96],"we":[97,139],"propose":[98],"MimicLM,":[99],"which":[100],"takes":[101],"novel":[103],"by":[105],"using":[106],"sources":[111],"retaining":[113],"real":[114,126],"recordings":[115],"targets.This":[117],"design":[118],"enables":[119],"learn":[123],"directly":[124],"from":[125],"distributions,":[128],"breaking":[129],"ceiling.Building":[133],"construction":[137],"approach,":[138],"incorporate":[140],"interleaved":[141],"text-audio":[142],"modeling":[143],"guide":[145],"generation":[147],"contentaccurate":[149],"apply":[152],"post-training":[153],"with":[154,176],"preference":[155],"alignment":[156],"mitigate":[158],"inherent":[160],"distributional":[161],"mismatch":[162],"data.Experiments":[167],"demonstrate":[168],"that":[169],"Mim-icLM":[170],"achieves":[171],"superior":[172],"simple":[178],"effective":[180],"architecture,":[181],"significantly":[182],"outperforming":[183],"existing":[184],"methods":[185],"in":[186],"naturalness":[187],"maintaining":[189],"competitive":[190],"similarity":[191],"scores":[192],"across":[193],"speaker":[194],"identity,":[195],"accent,":[196],"emotion":[198],"dimensions.":[199]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}