{"id":"https://openalex.org/W4385822596","doi":"https://doi.org/10.21437/interspeech.2023-1568","title":"ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation","display_name":"ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822596","doi":"https://doi.org/10.21437/interspeech.2023-1568"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.isca-archive.org/interspeech_2023/mehrish23_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065572305","display_name":"Ambuj Mehrish","orcid":"https://orcid.org/0000-0003-4240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ambuj Mehrish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035254621","display_name":"Abhinav Ramesh Kashyap","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Ramesh Kashyap","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076754984","display_name":"Yingting Li","orcid":"https://orcid.org/0000-0001-8661-0704"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yingting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007003459","display_name":"Navonil Majumder","orcid":"https://orcid.org/0000-0002-1449-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Navonil Majumder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033376109","display_name":"Soujanya Poria","orcid":"https://orcid.org/0000-0001-6924-7931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soujanya Poria","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":0.5085,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.55924901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4284","last_page":"4288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12588","display_name":"Electronic and Structural Properties of Oxides","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12588","display_name":"Electronic and Structural Properties of Oxides","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9509999752044678,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.757835865020752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6504919528961182},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5300245881080627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.395643949508667},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15114611387252808},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11583095788955688},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08441200852394104}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.757835865020752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6504919528961182},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5300245881080627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.395643949508667},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15114611387252808},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11583095788955688},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08441200852394104}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unive.it:10278/5105952","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5105952","pdf_url":"https://www.isca-archive.org/interspeech_2023/mehrish23_interspeech.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unive.it:10278/5105952","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5105952","pdf_url":"https://www.isca-archive.org/interspeech_2023/mehrish23_interspeech.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822596.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"There":[0],"are":[1,12,24],"significant":[2,110],"challenges":[3],"for":[4,9,17,86,139],"speaker":[5,76,114],"adaptation":[6],"in":[7,27,75,112],"textto-speech":[8],"languages":[10],"that":[11,23],"not":[13,25],"widely":[14],"spoken":[15],"or":[16,21],"speakers":[18,142],"with":[19,68],"accents":[20],"dialects":[22],"well-represented":[26],"the":[28,37,40,57,66,92,98,103,119,134],"training":[29],"data.":[30],"To":[31],"address":[32],"this":[33],"issue,":[34],"we":[35,95],"propose":[36],"use":[38],"of":[39,42,60,72,84,102,118,122],"\u201dmixture":[41],"adapters\u201d":[43],"method.":[44],"This":[45,107],"approach":[46,64,128],"involves":[47],"adding":[48],"multiple":[49],"adapters":[50],"within":[51],"a":[52,69,109,130],"backbone-model":[53],"layer":[54],"to":[55,133,141],"learn":[56],"unique":[58],"characteristics":[59],"different":[61],"speakers.":[62],"Our":[63],"outperforms":[65],"baseline,":[67],"noticeable":[70],"improvement":[71],"5%":[73],"observed":[74],"preference":[77],"tests":[78],"when":[79],"using":[80],"only":[81,97],"one":[82,117],"minute":[83],"data":[85],"each":[87],"new":[88],"speaker.":[89],"Moreover,":[90],"following":[91],"adapter":[93,99],"paradigm,":[94],"fine-tune":[96],"parameters":[100],"(11%":[101],"total":[104],"model":[105],"parameters).":[106],"is":[108],"achievement":[111],"parameter-efficient":[113],"adaptation,":[115],"and":[116],"first":[120],"models":[121],"its":[123],"kind.":[124],"Overall,":[125],"our":[126],"proposed":[127],"offers":[129],"promising":[131],"solution":[132],"speech":[135],"synthesis":[136],"techniques,":[137],"particularly":[138],"adapting":[140],"from":[143],"diverse":[144],"backgrounds.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}