{"id":"https://openalex.org/W7164477423","doi":"https://doi.org/10.1109/ojcs.2026.3696985","title":"Attention-Driven Alaryngeal Speech Enhancement via Discrete Representation Learning and Timbre-Preserving Augmentation","display_name":"Attention-Driven Alaryngeal Speech Enhancement via Discrete Representation Learning and Timbre-Preserving Augmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164477423","doi":"https://doi.org/10.1109/ojcs.2026.3696985"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2026.3696985","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2026.3696985","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/ojcs.2026.3696985","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093366571","display_name":"Hnin Yadana Lwin","orcid":"https://orcid.org/0009-0002-0746-8266"},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Hnin Yadana Lwin","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"],"raw_orcid":"https://orcid.org/0009-0002-0746-8266","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138519860","display_name":"Wuttipong Kumwilaisak","orcid":null},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Wuttipong Kumwilaisak","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-2957-6084","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029765234","display_name":"Chatchawarn Hansakunbuntheung","orcid":"https://orcid.org/0000-0003-4064-4882"},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chatchawarn Hansakunbuntheung","raw_affiliation_strings":["Digital Healthcare Platform Innovation Group, National Science and Technology Development Agency, Pathumthani, Thailand"],"raw_orcid":"https://orcid.org/0000-0003-4064-4882","affiliations":[{"raw_affiliation_string":"Digital Healthcare Platform Innovation Group, National Science and Technology Development Agency, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035810881","display_name":"Nattanun Thatphithakkul","orcid":"https://orcid.org/0000-0001-8240-2772"},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Nattanun Thatphithakkul","raw_affiliation_strings":["Digital Healthcare Platform Innovation Group, National Science and Technology Development Agency, Pathumthani, Thailand"],"raw_orcid":"https://orcid.org/0000-0001-8240-2772","affiliations":[{"raw_affiliation_string":"Digital Healthcare Platform Innovation Group, National Science and Technology Development Agency, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76100132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"1236","last_page":"1247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.917900025844574,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.917900025844574,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.021299999207258224,"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":0.019200000911951065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.515999972820282},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5149000287055969},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3111000061035156},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.30140000581741333},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2752000093460083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6072999835014343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217000246047974},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.515999972820282},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5149000287055969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2026.3696985","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2026.3696985","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7f66911448e44f0b894f4df872e18f24","is_oa":false,"landing_page_url":"https://doaj.org/article/7f66911448e44f0b894f4df872e18f24","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 7, Pp 1236-1247 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2026.3696985","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2026.3696985","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5123695135116577}],"awards":[{"id":"https://openalex.org/G1191463953","display_name":null,"funder_award_id":"N42A670175","funder_id":"https://openalex.org/F4320322817","funder_display_name":"National Research Council of Thailand"}],"funders":[{"id":"https://openalex.org/F4320322817","display_name":"National Research Council of Thailand","ror":"https://ror.org/018wfhg78"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Alaryngeal":[0],"speech":[1],"enhancement":[2],"seeks":[3],"to":[4,27,178],"restore":[5],"intelligibility":[6],"and":[7,32,48,57,104,147,170],"naturalness":[8],"for":[9,141],"individuals":[10],"who":[11],"have":[12],"undergone":[13],"laryngectomy.":[14],"Existing":[15],"methods":[16],"based":[17],"on":[18,145],"direct":[19],"spectral":[20],"mapping":[21],"or":[22,163],"frame-level":[23],"voice":[24],"conversion":[25],"fail":[26],"exploit":[28],"speech's":[29],"linguistic":[30],"structure":[31],"are":[33,54],"constrained":[34],"by":[35,59,72],"scarce":[36],"pathological":[37],"data.":[38],"We":[39],"propose":[40],"a":[41,60,87,94,105,129,137],"multi-stage":[42],"framework":[43],"integrating":[44],"discrete":[45],"representation":[46],"learning":[47],"attention-driven":[49],"feature":[50],"alignment.":[51],"WavLM":[52],"embeddings":[53],"quantized":[55],"via$k$-means":[56],"refined":[58],"Speech":[61],"Language":[62],"Model":[63],"that":[64,108],"maps":[65],"alaryngeal":[66],"tokens":[67],"toward":[68],"normal-speech":[69,102],"tokens,":[70],"followed":[71],"Conformer-based":[73],"reconstruction.":[74],"An":[75],"Attention-Driven":[76],"Feature":[77,89],"Matcher":[78,97],"(ADFM)":[79],"then":[80],"refines":[81],"features":[82],"through":[83],"three":[84],"coupled":[85],"modules:":[86],"residual":[88],"Enhancer":[90],"with":[91,136,161],"learnable":[92],"scaling,":[93],"Multi-Head":[95],"Attention":[96],"performing":[98],"soft":[99],"alignment":[100],"over$k$-nearest":[101],"neighbors,":[103],"Quality":[106],"Predictor":[107],"estimates":[109],"per-frame":[110],"confidence":[111],"as":[112],"an":[113],"inference-time":[114],"reliability":[115],"indicator.":[116],"A":[117],"HiFi-GAN":[118],"vocoder":[119],"synthesizes":[120],"the":[121],"waveform.":[122],"To":[123],"overcome":[124],"data":[125],"scarcity,":[126],"we":[127],"introduce":[128],"Multi-Mask":[130],"GAN":[131],"augmentation":[132],"strategy":[133],"extending":[134],"MaskCycleGAN-VC":[135],"timbre":[138],"similarity":[139,153],"loss":[140],"speaker-identity":[142],"preservation.":[143],"Evaluations":[144],"Thai":[146],"English":[148],"corpora":[149],"show":[150],"best":[151],"speaker":[152],"in":[154],"both":[155],"languages":[156],"(0.858":[157],"Thai,":[158,167,173],"0.850":[159],"English)":[160,169],"competitive":[162],"state-of-the-art":[164],"FAD":[165,180],"(5.252":[166],"5.385":[168],"MCD":[171],"(5.644":[172],"5.322":[174],"English),":[175],"yielding":[176],"up":[177],"27.3%":[179],"reduction":[181],"over":[182],"kNN-VC.":[183],"Subjective":[184],"tests":[185],"confirm":[186],"significant":[187],"listener":[188],"preference":[189],"(77%":[190],"English,":[191],"67%":[192],"Thai).":[193]},"counts_by_year":[],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-06-13T00:00:00"}