{"id":"https://openalex.org/W4389111299","doi":"https://doi.org/10.1145/3628454.3631582","title":"Alaryngeal Speech Generation Using MaskCycleGAN-VC and Timbre-Enhanced Loss","display_name":"Alaryngeal Speech Generation Using MaskCycleGAN-VC and Timbre-Enhanced Loss","publication_year":2023,"publication_date":"2023-11-28","ids":{"openalex":"https://openalex.org/W4389111299","doi":"https://doi.org/10.1145/3628454.3631582"},"language":"en","primary_location":{"id":"doi:10.1145/3628454.3631582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628454.3631582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628454.3631582","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Advances in Information Technology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3628454.3631582","any_repository_has_fulltext":null},"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":["King Mongkut's University of Technology Thonburi, Thailand"],"raw_orcid":"https://orcid.org/0009-0002-0746-8266","affiliations":[{"raw_affiliation_string":"King Mongkut's University of Technology Thonburi, Thailand","institution_ids":["https://openalex.org/I60837268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022390828","display_name":"Wuttipong Kumwilaisak","orcid":"https://orcid.org/0000-0002-2957-6084"},"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":["King Mongkut's University of Technology Thonburi, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-2957-6084","affiliations":[{"raw_affiliation_string":"King Mongkut's University of Technology Thonburi, 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":["National Science and Technology Development Agency, Thailand"],"raw_orcid":"https://orcid.org/0000-0003-4064-4882","affiliations":[{"raw_affiliation_string":"National Science and Technology Development Agency, 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":["National Science and Technology Development Agency, Thailand"],"raw_orcid":"https://orcid.org/0000-0001-8240-2772","affiliations":[{"raw_affiliation_string":"National Science and Technology Development Agency, Thailand","institution_ids":["https://openalex.org/I1332092204"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/masking","display_name":"Masking (illustration)","score":0.8259673118591309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7812291383743286},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7427569627761841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299423813819885},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4723944365978241},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.08539804816246033}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.8259673118591309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7812291383743286},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7427569627761841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299423813819885},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4723944365978241},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.08539804816246033},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628454.3631582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628454.3631582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628454.3631582","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Advances in Information Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3628454.3631582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628454.3631582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628454.3631582","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Advances in Information Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389111299.pdf","grobid_xml":"https://content.openalex.org/works/W4389111299.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2181680948","https://openalex.org/W2339754110","https://openalex.org/W2593414223","https://openalex.org/W2937579788","https://openalex.org/W2972478942","https://openalex.org/W3162512456","https://openalex.org/W4297841464","https://openalex.org/W6685569815"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W3109975354","https://openalex.org/W2124576126","https://openalex.org/W1984264321","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299"],"abstract_inverted_index":{"This":[0,106],"paper":[1],"introduces":[2],"a":[3,92],"data":[4],"augmentation":[5],"technique":[6,42],"for":[7,44,66],"alaryngeal":[8,67,81,134],"speech":[9,82],"using":[10,124],"voice":[11,64,76,119],"conversion":[12,65,111],"within":[13,46,78],"the":[14,29,47,59,73,79,97,102,110,128,140],"MaskCycleGAN-VC":[15,48],"framework":[16,49],"[6].":[17],"Our":[18],"method":[19,130],"leverages":[20],"two":[21],"masking":[22,45,56],"techniques:":[23],"Articulatory":[24],"Dimension":[25],"Masking":[26,36],"(ADM)":[27],"and":[28,52,61],"combination":[30],"of":[31,63,75],"ADM":[32],"with":[33],"Consecutive":[34],"Time":[35],"(CTM),":[37],"called":[38],"SpecAugment[11].":[39],"The":[40],"initial":[41],"used":[43],"is":[50,90],"CTM,":[51],"our":[53,88,122],"proposed":[54,129],"additional":[55],"techniques":[57],"enhance":[58],"quality":[60],"performance":[62],"speech.":[68],"We":[69],"can":[70,131],"also":[71],"expand":[72],"variability":[74],"characteristics":[77,117,137],"converted":[80],"dataset.":[83],"One":[84],"notable":[85],"enhancement":[86],"in":[87],"approach":[89],"incorporating":[91],"timbre":[93],"similarity":[94],"score":[95,107],"into":[96],"generator":[98],"loss,":[99],"known":[100],"as":[101],"Timbre":[103],"Enhanced":[104],"Loss.":[105],"dynamically":[108],"guides":[109],"process":[112],"to":[113,139],"prioritize":[114],"preserving":[115],"timbral":[116],"during":[118],"transformation.":[120],"From":[121],"experiments":[123],"different":[125],"objective":[126],"metrics,":[127],"provide":[132],"synthesized":[133],"speeches":[135],"having":[136],"close":[138],"actual":[141],"ones.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
