{"id":"https://openalex.org/W4415524317","doi":"https://doi.org/10.1109/mlsp62443.2025.11204217","title":"Unseen Speaker and Language Adaptation for Lightweight Text-to-Speech with Adapters","display_name":"Unseen Speaker and Language Adaptation for Lightweight Text-to-Speech with Adapters","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524317","doi":"https://doi.org/10.1109/mlsp62443.2025.11204217"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5010492282","display_name":"Alessio Falai","orcid":"https://orcid.org/0000-0002-6574-5607"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessio Falai","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004044","display_name":"Ziyao Zhang","orcid":"https://orcid.org/0000-0002-0617-1340"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyao Zhang","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120126659","display_name":"Akos Gangoly","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akos Gangoly","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9882000088691711,"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":0.9882000088691711,"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":0.9557999968528748,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9394999742507935,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/adaptation","display_name":"Adaptation (eye)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.41130000352859497},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4092000126838684},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40220001339912415},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3391000032424927},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.334199994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846999764442444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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":28,"referenced_works":["https://openalex.org/W2292984643","https://openalex.org/W2525412388","https://openalex.org/W2531409750","https://openalex.org/W2560647685","https://openalex.org/W2752782242","https://openalex.org/W2889358387","https://openalex.org/W2889562042","https://openalex.org/W2890184085","https://openalex.org/W2945648216","https://openalex.org/W2962788625","https://openalex.org/W2963964591","https://openalex.org/W2972473628","https://openalex.org/W3015338123","https://openalex.org/W3097515180","https://openalex.org/W3097911750","https://openalex.org/W3101498587","https://openalex.org/W3144035034","https://openalex.org/W3160919572","https://openalex.org/W3196584150","https://openalex.org/W3197273793","https://openalex.org/W3198712976","https://openalex.org/W4283824751","https://openalex.org/W4296069158","https://openalex.org/W4372260337","https://openalex.org/W4372346804","https://openalex.org/W4385822455","https://openalex.org/W4385822596","https://openalex.org/W4385993937"],"related_works":[],"abstract_inverted_index":{"In":[0,21],"this":[1],"paper":[2,121],"we":[3,23,104],"investigate":[4],"cross-lingual":[5],"Text-To-Speech":[6],"(TTS)":[7],"synthesis":[8],"through":[9],"the":[10,15,25,34,47,59,84,96,126,133],"lens":[11],"of":[12,17,27,36,61,83,102,128,135],"adapters,":[13],"in":[14,41,45,63,100,116],"context":[16],"lightweight":[18],"TTS":[19],"systems.":[20],"particular,":[22],"compare":[24],"tasks":[26],"unseen":[28,74],"speaker":[29,75,87],"and":[30,66,106,132],"language":[31,89],"adaptation":[32],"with":[33],"goal":[35],"synthesising":[37],"a":[38,42],"target":[39,43,48],"voice":[40,49],"language,":[44],"which":[46],"has":[50],"no":[51],"recordings":[52],"therein.":[53],"Results":[54],"from":[55],"objective":[56,109],"evaluations":[57],"demonstrate":[58],"effectiveness":[60],"adapters":[62],"learning":[64],"language-specific":[65],"speaker-specific":[67],"information,":[68],"allowing":[69],"pre-trained":[70],"models":[71],"to":[72,92],"learn":[73],"identities":[76],"or":[77,88],"languages,":[78],"while":[79],"avoiding":[80],"catastrophic":[81],"forgetting":[82],"original":[85],"model's":[86],"information.":[90],"Additionally,":[91],"measure":[93],"how":[94],"native":[95],"generated":[97],"voices":[98],"are":[99],"terms":[101],"accent,":[103],"propose":[105],"validate":[107],"an":[108],"metric":[110],"inspired":[111],"by":[112],"mispronunciation":[113],"detection":[114],"techniques":[115],"second-language":[117],"(L2)":[118],"learners.":[119],"The":[120],"also":[122],"provides":[123],"insights":[124],"into":[125],"impact":[127],"adapter":[129],"placement,":[130],"configuration":[131],"number":[134],"speakers":[136],"used.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}