{"id":"https://openalex.org/W4405634116","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800072","title":"Continual Gated Adapter for Bilingual Codec Text-to-Speech","display_name":"Continual Gated Adapter for Bilingual Codec Text-to-Speech","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405634116","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800072"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5016250453","display_name":"Li-Jen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Jen Yang","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":0.979200005531311,"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":0.979200005531311,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9204999804496765,"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/adapter","display_name":"Adapter (computing)","score":0.7710189819335938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7638700008392334},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7278014421463013},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6144289970397949},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5796060562133789},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.486272931098938},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.42822757363319397},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2513217031955719},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22979050874710083},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.21956917643547058},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17409738898277283}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7710189819335938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638700008392334},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7278014421463013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6144289970397949},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5796060562133789},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.486272931098938},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.42822757363319397},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2513217031955719},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22979050874710083},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.21956917643547058},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17409738898277283}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2963242190","https://openalex.org/W3016139610","https://openalex.org/W3038083940","https://openalex.org/W3089628124","https://openalex.org/W3095012670","https://openalex.org/W3097032879","https://openalex.org/W3167533889","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4297841576","https://openalex.org/W4319585922","https://openalex.org/W4381786045","https://openalex.org/W4385572883","https://openalex.org/W4385822470","https://openalex.org/W4388820551","https://openalex.org/W4391021740","https://openalex.org/W4396982391","https://openalex.org/W4402111729","https://openalex.org/W4402111999","https://openalex.org/W6719384148","https://openalex.org/W6759579507","https://openalex.org/W6761768988","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6790220310","https://openalex.org/W6792462441","https://openalex.org/W6793783828","https://openalex.org/W6846857581","https://openalex.org/W6847363464","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W2060409740","https://openalex.org/W2382399415","https://openalex.org/W2374470469","https://openalex.org/W2129079178","https://openalex.org/W2159899134","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2129913000","https://openalex.org/W2787189739"],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"system":[2],"has":[3],"achieved":[4],"desirable":[5],"performance":[6],"in":[7,124],"monolingual":[8,34],"setting":[9],"with":[10,52,69,115],"high-resourced":[11],"data.":[12],"However,":[13],"it":[14],"is":[15,67,86,104],"challenging":[16],"to":[17,88,96,106,110],"carry":[18],"out":[19],"the":[20,27,131],"cross-lingual":[21,41],"low-resourced":[22,45],"voice":[23,42],"cloning":[24,43],"by":[25,32,56,129],"utilizing":[26],"pre-trained":[28],"multilingual":[29],"model":[30],"given":[31],"a":[33,57,63,77,99,121],"speaker.":[35],"This":[36],"paper":[37],"presents":[38],"an":[39,70],"adaptive":[40],"under":[44],"scenario":[46],"which":[47],"can":[48],"be":[49],"flexibly":[50],"performed":[51],"speech":[53,65],"prompt":[54],"driven":[55],"neural":[58],"codec":[59,79],"TTS.":[60],"In":[61],"particular,":[62],"few-shot":[64],"synthesizer":[66],"leveraged":[68],"adapter":[71,103],"tuning":[72],"for":[73],"speaker":[74,127],"adaptation":[75],"on":[76],"bilingual":[78],"backbone":[80],"model.":[81],"The":[82],"rehearsal-based":[83],"continual":[84,132],"learning":[85],"implemented":[87],"avoid":[89],"forgetting":[90],"of":[91],"source":[92],"language":[93],"data":[94],"due":[95],"fine-tuning.":[97],"Importantly,":[98],"novel":[100],"learnable":[101],"gated":[102,133],"introduced":[105],"enable":[107],"conditional":[108],"computation":[109],"handle":[111],"different":[112],"input":[113],"features":[114],"specialized":[116],"adjustment.":[117],"Experimental":[118],"results":[119],"show":[120],"significant":[122],"improvement":[123],"naturalness":[125],"and":[126],"similarity":[128],"using":[130],"adapter.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}