{"id":"https://openalex.org/W4416799076","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249051","title":"Improving Exemplar-Based Electrolaryngeal Speech Voice Conversion Via Robust Content Representations","display_name":"Improving Exemplar-Based Electrolaryngeal Speech Voice Conversion Via Robust Content Representations","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799076","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249051"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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/A5041816119","display_name":"Fo-Rui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Fo-Rui Li","raw_affiliation_strings":["National Central University,Dept. of Biomedical Science and Engineering,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Dept. of Biomedical Science and Engineering,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111385896","display_name":"Hsin-Te Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Te Hwang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014941783","display_name":"Ming-Chi Yen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Chi Yen","raw_affiliation_strings":["Institute of Information Science, Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047456186","display_name":"Men\u2010Tzung Lo","orcid":"https://orcid.org/0000-0003-2630-4945"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Men-Tung Lo","raw_affiliation_strings":["National Central University,Dept. of Biomedical Science and Engineering,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Dept. of Biomedical Science and Engineering,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041816119"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20716002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"730","last_page":"735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6848999857902527,"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":0.6848999857902527,"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/T10863","display_name":"Voice and Speech Disorders","score":0.1615999937057495,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.07129999995231628,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7322999835014343},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6808000206947327},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4936000108718872},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47029998898506165},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44749999046325684},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4187999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440000176429749},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7322999835014343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901999711990356},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47029998898506165},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4472000002861023},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2022125261","https://openalex.org/W2064525251","https://openalex.org/W2128160875","https://openalex.org/W2895118591","https://openalex.org/W2902967674","https://openalex.org/W2995181338","https://openalex.org/W3119308075","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4306155393","https://openalex.org/W4313473473","https://openalex.org/W4385822466","https://openalex.org/W4385823432","https://openalex.org/W4392902750","https://openalex.org/W4392909515","https://openalex.org/W4402111636","https://openalex.org/W4402981815","https://openalex.org/W4405633323","https://openalex.org/W4406462037","https://openalex.org/W4411599582"],"related_works":[],"abstract_inverted_index":{"Electrolaryngeal":[0],"speech":[1,67,85],"voice":[2],"conversion":[3],"(ELVC)":[4],"aims":[5],"to":[6,50],"improve":[7,66],"the":[8,21,41,102,115,128],"naturalness":[9],"and":[10,47,98,110,122],"intelligibility":[11],"of":[12,24,44,130],"electrolaryngeal":[13],"(EL)":[14],"speech.":[15],"A":[16],"key":[17],"challenge":[18],"lies":[19],"in":[20],"limited":[22],"availability":[23],"EL":[25],"data.":[26],"We":[27],"previously":[28],"proposed":[29],"a":[30,89],"locally":[31],"linear":[32],"embeddingbased":[33],"ELVC":[34],"(LLE-ELVC)":[35],"method":[36,93],"that":[37,60],"leverages":[38],"features":[39,76,83],"from":[40],"sixth":[42],"layer":[43],"WavLM":[45,106],"Large":[46,112],"exemplar-based":[48],"techniques":[49],"reduce":[51],"reliance":[52],"on":[53,57,88],"large":[54],"corpora.":[55],"Building":[56],"recent":[58],"findings":[59],"using":[61],"advanced":[62],"content":[63,75,132],"representations":[64,133],"can":[65],"quality,":[68],"we":[69],"extend":[70],"LLE-ELVC":[71],"by":[72],"incorporating":[73],"robust":[74,117],"for":[77,84],"neighbor":[78],"search":[79],"while":[80],"retaining":[81],"prosody-rich":[82],"reconstruction.":[86],"Evaluated":[87],"Mandarin":[90],"corpus,":[91],"our":[92],"consistently":[94],"improves":[95],"both":[96],"objective":[97],"subjective":[99],"metrics.":[100],"Among":[101],"foundation":[103],"models":[104],"evaluated,":[105],"Large,":[107,109],"Chinese-HuBERT":[108],"Whisper":[111],"V3":[113],"show":[114],"most":[116],"performance":[118],"across":[119],"different":[120],"speakers":[121],"recording":[123],"conditions.":[124],"These":[125],"results":[126],"confirm":[127],"effectiveness":[129],"integrating":[131],"into":[134],"LLE-ELVC.":[135]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}