{"id":"https://openalex.org/W4416252318","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227557","title":"TV-MDiff: A Zero-Shot Text-To-Speech and Zero-Shot Voice Conversion System with Mamba-Based Diffusion Model","display_name":"TV-MDiff: A Zero-Shot Text-To-Speech and Zero-Shot Voice Conversion System with Mamba-Based Diffusion Model","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252318","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227557"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100750044","display_name":"Zhihua Huang","orcid":"https://orcid.org/0000-0003-0880-1622"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115598124","display_name":"Ke Chen","orcid":"https://orcid.org/0009-0005-3069-9769"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.9325000047683716,"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":0.9325000047683716,"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":0.04899999871850014,"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/T10863","display_name":"Voice and Speech Disorders","score":0.005799999926239252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5371999740600586},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4846000075340271},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4722999930381775},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4092999994754791},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.35850000381469727},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3492000102996826},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3352999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7404999732971191},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5371999740600586},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43050000071525574},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4092999994754791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":21,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2747874407","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W3097777922","https://openalex.org/W3140429000","https://openalex.org/W3161695192","https://openalex.org/W3198533616","https://openalex.org/W3205878676","https://openalex.org/W3210530853","https://openalex.org/W4221156079","https://openalex.org/W4304099317","https://openalex.org/W4372260261","https://openalex.org/W4385245566","https://openalex.org/W4385822697","https://openalex.org/W4385823264","https://openalex.org/W4386083034","https://openalex.org/W4392930780","https://openalex.org/W4393156644","https://openalex.org/W4393160753","https://openalex.org/W4402952320"],"related_works":[],"abstract_inverted_index":{"Many":[0],"studies":[1],"have":[2],"proposed":[3],"zero-shot":[4],"(ZS)":[5],"speaker":[6,22,45,181],"adaptation":[7,46],"methods":[8,37],"for":[9,19,70,128,149,185],"Text-To-Speech":[10],"(TTS)":[11],"and":[12,96,109,123,183,189,204],"Voice":[13],"Conversion":[14],"(VC)":[15],"to":[16,81,114,134,209],"synthesize":[17],"speech":[18,26,107,170],"an":[20],"unseen":[21],"from":[23,66,77],"a":[24,93,142],"reference":[25],"segment":[27],"without":[28],"additional":[29],"training.":[30,71],"However,":[31],"the":[32,60,64,75,101,111,136,146,150,160,169],"models":[33],"developed":[34],"using":[35,67],"these":[36,116],"do":[38],"not":[39],"fully":[40],"utilize":[41],"their":[42],"learned":[43],"ZS":[44,54,57,94,97,121,124,187,190,198],"capability":[47,200],"because":[48],"they":[49],"can":[50,205],"only":[51],"perform":[52],"either":[53],"TTS":[55,61,95,122,188,199],"or":[56],"VC.":[58],"Additionally,":[59],"task":[62],"restricts":[63],"model":[65,76,113,115,161,174],"untranscribed":[68,79,132],"data":[69,80,133],"This":[72],"limitation":[73],"prevents":[74],"leveraging":[78],"further":[82,129],"enhance":[83,135],"its":[84,197],"overall":[85],"performance.":[86,138],"In":[87],"this":[88],"paper,":[89],"we":[90,140],"propose":[91],"TV-MDiff,":[92],"VC":[98,125,191],"system":[99],"with":[100,131],"Mamba-based":[102,143],"diffusion":[103,112,151],"model.":[104],"We":[105],"decouple":[106],"features":[108],"use":[110],"decoupled":[117],"attributes,":[118],"thus":[119],"achieving":[120],"while":[126,158],"allowing":[127],"training":[130],"model\u2019s":[137],"Moreover,":[139],"introduce":[141],"WaveNet":[144],"as":[145],"denoising":[147],"network":[148],"model,":[152],"which":[153],"improves":[154],"sample":[155],"generation":[156],"quality":[157,184],"keeping":[159],"parameters":[162],"relatively":[163],"small.":[164],"The":[165],"experiments":[166],"demonstrate":[167],"that":[168,196],"generated":[171],"by":[172],"our":[173],"achieves":[175],"good":[176],"results":[177],"in":[178],"terms":[179],"of":[180],"similarity":[182],"both":[186],"tasks.":[192],"Further":[193],"exploration":[194],"reveals":[195],"is":[201],"highly":[202],"transferable":[203],"be":[206],"easily":[207],"adapted":[208],"another":[210],"language.":[211],"Audio":[212],"samples":[213],"are":[214],"available:":[215],"https://echohzh.github.io/TV-MDiff/.":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}