{"id":"https://openalex.org/W4415821790","doi":"https://doi.org/10.1109/ro-man63969.2025.11217801","title":"Parameter-Efficient Personalized Speech Synthesis via EMD-based Speaker Modeling","display_name":"Parameter-Efficient Personalized Speech Synthesis via EMD-based Speaker Modeling","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415821790","doi":"https://doi.org/10.1109/ro-man63969.2025.11217801"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5111103714","display_name":"Chengxi Lei","orcid":"https://orcid.org/0009-0003-5799-5977"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Chengxi Lei","raw_affiliation_strings":["Massey University,School of Mathematical and Computational Sciences,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massey University,School of Mathematical and Computational Sciences,New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041651091","display_name":"Feng Hou","orcid":"https://orcid.org/0000-0001-5776-9177"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Feng Hou","raw_affiliation_strings":["Massey University,School of Mathematical and Computational Sciences,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massey University,School of Mathematical and Computational Sciences,New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010474876","display_name":"Huia Tomlins Jahnke","orcid":null},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Huia Jahnke","raw_affiliation_strings":["Massey University,School of Māori and Multicultural Education,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massey University,School of Māori and Multicultural Education,New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022594144","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0003-2899-9816"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["Massey University,School of Mathematical and Computational Sciences,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massey University,School of Mathematical and Computational Sciences,New Zealand","institution_ids":["https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51158804"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28454191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"551","last_page":"556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9445000290870667,"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":0.9445000290870667,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.006599999964237213,"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/T11448","display_name":"Face recognition and analysis","score":0.006500000134110451,"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/naturalness","display_name":"Naturalness","score":0.826200008392334},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5508000254631042},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5034999847412109},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.42239999771118164},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.39259999990463257},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3856000006198883}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.826200008392334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113999962806702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6876999735832214},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5508000254631042},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C25570617","wikidata":"https://www.wikidata.org/wiki/Q1006462","display_name":"Hilbert\u2013Huang transform","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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":17,"referenced_works":["https://openalex.org/W2974743569","https://openalex.org/W3013018143","https://openalex.org/W3015826515","https://openalex.org/W3016159759","https://openalex.org/W3116857504","https://openalex.org/W3135169846","https://openalex.org/W3161296985","https://openalex.org/W3193618782","https://openalex.org/W4206147466","https://openalex.org/W4225320802","https://openalex.org/W4292455922","https://openalex.org/W4297841547","https://openalex.org/W4306942161","https://openalex.org/W4372259784","https://openalex.org/W4372260242","https://openalex.org/W4386133927","https://openalex.org/W4395447377"],"related_works":[],"abstract_inverted_index":{"Personalized":[0],"speech":[1,15,57],"synthesis":[2,58],"has":[3],"attracted":[4],"increasing":[5],"attention":[6],"in":[7,124],"the":[8,22,29,50,80,111,122,134,140],"field":[9],"of":[10,25,142],"robotics.":[11],"Compared":[12],"to":[13,39,83,102,151],"traditional":[14],"synthesis,":[16],"it":[17,144],"faces":[18],"two":[19],"primary":[20],"challenges:":[21],"limited":[23],"availability":[24],"adaptation":[26,34,104,136],"data":[27],"and":[28,44,98,127,153],"necessity":[30],"for":[31],"highly":[32],"efficient":[33],"method":[35,69,137],"using":[36,110],"compact":[37],"parameters":[38],"reduce":[40],"both":[41,49,125],"training":[42],"time":[43],"memory":[45],"consumption.":[46],"To":[47],"address":[48],"challenges,":[51],"this":[52],"paper":[53],"proposes":[54],"a":[55,71,91],"personalized":[56],"approach":[59,109,120],"that":[60,117],"incorporates":[61],"an":[62],"Empirical":[63],"Mode":[64],"Decomposition":[65],"(EMD)-based":[66],"speaker":[67],"modeling":[68],"alongside":[70],"novel":[72],"decoder":[73],"structure":[74],"with":[75],"masked":[76],"inputs,":[77],"which":[78],"improves":[79],"model\u2019s":[81],"ability":[82],"extract":[84],"speaker-specific":[85],"features":[86],"accurately.":[87],"Furthermore,":[88],"we":[89],"introduce":[90],"parameter-efficient":[92],"fine-tuning":[93,155],"technique,":[94],"Attention-based":[95],"Speaker-Text":[96],"Scaling":[97],"Shifting":[99],"Feature":[100],"(AST-SSF),":[101],"enhance":[103],"efficiency.":[105],"We":[106],"validate":[107],"our":[108,118],"MAGICDATA":[112],"Corpus.":[113],"The":[114],"results":[115],"indicate":[116],"proposed":[119,135],"outperforms":[121],"baseline":[123],"naturalness":[126],"similarity,":[128],"demonstrating":[129],"its":[130],"effectiveness.":[131],"Moreover,":[132],"although":[133],"substantially":[138],"reduces":[139],"number":[141],"parameters,":[143],"exhibits":[145],"only":[146],"minimal":[147],"performance":[148],"degradation":[149],"compared":[150],"full":[152],"partial":[154],"strategies.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-03T00:00:00"}