{"id":"https://openalex.org/W4407692478","doi":"https://doi.org/10.1109/lsp.2025.3543456","title":"UnitDiff: A Unit-Diffusion Model for Code-Switching Speech Synthesis","display_name":"UnitDiff: A Unit-Diffusion Model for Code-Switching Speech Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407692478","doi":"https://doi.org/10.1109/lsp.2025.3543456"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3543456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3543456","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/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":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0005-3069-9769","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihua Huang","orcid":"https://orcid.org/0009-0001-0973-4401"},"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":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0001-0973-4401","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Yonghong Yan","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6907-5770","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82312994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"1051","last_page":"1055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9800999760627747,"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":0.9800999760627747,"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/T12031","display_name":"Speech and dialogue systems","score":0.9742000102996826,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9733999967575073,"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/computer-science","display_name":"Computer science","score":0.643742561340332},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5696494579315186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5494890213012695},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5203649401664734},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5190049409866333},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5158859491348267},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5078654885292053},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.4663879871368408},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29305052757263184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14073041081428528},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08215564489364624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643742561340332},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5696494579315186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5494890213012695},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5203649401664734},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5190049409866333},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5158859491348267},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5078654885292053},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.4663879871368408},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29305052757263184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14073041081428528},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08215564489364624},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3543456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3543456","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6160969776","display_name":null,"funder_award_id":"12464060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2525997790","https://openalex.org/W2936832667","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2973084242","https://openalex.org/W2996952407","https://openalex.org/W3016139610","https://openalex.org/W3095873922","https://openalex.org/W3205154814","https://openalex.org/W3210530853","https://openalex.org/W4304099317","https://openalex.org/W4372260486","https://openalex.org/W4385823402","https://openalex.org/W4391615163","https://openalex.org/W4392903591","https://openalex.org/W4392904694","https://openalex.org/W4402979375","https://openalex.org/W6679045638","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6805710207","https://openalex.org/W6809884996","https://openalex.org/W6847363464","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2053531689","https://openalex.org/W1842536210"],"abstract_inverted_index":{"Given":[0],"the":[1,29,37,51,57,98,103,111],"scarcity":[2],"of":[3,36,110],"Code-Switching":[4],"(CS)":[5],"datasets,":[6],"most":[7],"researchers":[8],"synthesize":[9],"CS":[10,23,45,113],"speech":[11,46,93],"using":[12],"multiple":[13],"monolingual":[14],"datasets.":[15],"However,":[16],"this":[17],"approach":[18,78],"presents":[19],"challenges":[20],"in":[21,101],"synthesizing":[22],"speech,":[24],"such":[25],"as":[26],"difficulty":[27],"controlling":[28],"speaker's":[30],"identity":[31],"and":[32,107],"causing":[33],"low":[34],"intelligibility":[35],"generated":[38,112],"speech.":[39,114],"This":[40,77],"letter":[41],"proposes":[42],"UnitDiff,":[43],"a":[44,70],"synthesis":[47],"model":[48,55],"based":[49],"on":[50],"unit-diffusion":[52],"framework.":[53],"The":[54],"employs":[56],"self-supervised":[58],"high-level":[59],"representation":[60],"\u2019soft":[61],"unit'":[62],"extracted":[63],"from":[64],"soft":[65],"HuBERT":[66],"to":[67,91],"directly":[68],"predict":[69],"clean":[71],"mel-spectrogram":[72],"<inline-formula":[73],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[74],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[75],"notation=\"LaTeX\">$x_{0}$</tex-math></inline-formula>.":[76],"enhances":[79],"control":[80],"over":[81],"speaker":[82,105,108],"identity.":[83],"A":[84],"language":[85],"tagging":[86],"method":[87],"is":[88],"also":[89],"introduced":[90],"improve":[92],"intelligibility.":[94],"Evaluation":[95],"results":[96],"validate":[97],"model's":[99],"effectiveness":[100],"improving":[102],"intelligibility,":[104],"similarity,":[106],"consistency":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
