{"id":"https://openalex.org/W4408610945","doi":"https://doi.org/10.1109/icaiic64266.2025.10920769","title":"BemaGANv2: A Vocoder with Superior Periodicity Capture for Long-Term Audio Generation","display_name":"BemaGANv2: A Vocoder with Superior Periodicity Capture for Long-Term Audio Generation","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4408610945","doi":"https://doi.org/10.1109/icaiic64266.2025.10920769"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic64266.2025.10920769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5008603856","display_name":"T. H. Park","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Taesoo Park","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103756762","display_name":"Mungwi Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mungwi Jeong","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103258600","display_name":"M Park","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mingyu Park","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833116","display_name":"Narae Kim","orcid":"https://orcid.org/0000-0001-7354-5974"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Narae Kim","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383374","display_name":"Junyoung Kim","orcid":"https://orcid.org/0000-0003-4815-2655"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junyoung Kim","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596568","display_name":"Dohyun Park","orcid":"https://orcid.org/0000-0002-8748-1497"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dohyun Park","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112946719","display_name":"Mujung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mujung Kim","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100925158","display_name":"Ji\u2010Sang Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisang Yoo","raw_affiliation_strings":["Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Department of Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075722249","display_name":"H.-W. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoyun Lee","raw_affiliation_strings":["Ewha Womans University College of Medicine,Department of Otorhinolaryngology-Head and Neck Surgery,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University College of Medicine,Department of Otorhinolaryngology-Head and Neck Surgery,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393347","display_name":"Sang\u2010Hoon Kim","orcid":"https://orcid.org/0000-0002-8867-8822"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghoon Kim","raw_affiliation_strings":["School of Medicine, Kyung Hee University,Department of Otorhinolaryngology, Head and Neck Surgery,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"School of Medicine, Kyung Hee University,Department of Otorhinolaryngology, Head and Neck Surgery,Seoul,South Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044901165","display_name":"Soonchul Kwon","orcid":"https://orcid.org/0000-0001-6595-6415"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonchul Kwon","raw_affiliation_strings":["Graduate School of Smart Convergence, Kwangwoon University,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Smart Convergence, Kwangwoon University,Seoul,South Korea","institution_ids":["https://openalex.org/I161024014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5008603856"],"corresponding_institution_ids":["https://openalex.org/I161024014"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06898198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"0830","last_page":"0834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9872999787330627,"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":0.973800003528595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7730109691619873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605259776115417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5594663619995117},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06362906098365784}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7730109691619873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605259776115417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5594663619995117},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06362906098365784},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic64266.2025.10920769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":10,"referenced_works":["https://openalex.org/W2087309216","https://openalex.org/W2107860279","https://openalex.org/W2133665775","https://openalex.org/W2593414223","https://openalex.org/W6736155344","https://openalex.org/W6757220786","https://openalex.org/W6779577414","https://openalex.org/W6783867762","https://openalex.org/W6785954764","https://openalex.org/W6838843145"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"BemaGANv2,":[3],"an":[4],"advanced":[5],"model":[6,43,102,139],"built":[7],"upon":[8],"the":[9,14,18,32,36,40,42,54,59,65,68,71,78,81,95,116,122,137],"BemaGAN":[10,73],"architecture.":[11],"BemaGANv2":[12,101,135],"enhances":[13],"Generator":[15],"and":[16,28,51,64,92,124,143],"extends":[17],"discriminator":[19,69,87],"framework":[20],"to":[21,47,80,114,120],"more":[22,149],"effectively":[23],"capture":[24],"long-term":[25,129,152],"audio":[26,49,153],"dependencies":[27],"periodicity.":[29,52],"By":[30],"applying":[31],"Snake":[33],"function":[34,38],"as":[35,104],"activation":[37],"in":[39,58,70,107,140],"Generator,":[41],"improves":[44],"its":[45],"ability":[46],"handle":[48],"extrapolation":[50],"Additionally,":[53],"envelope":[55],"extraction":[56],"method":[57],"MED":[60],"has":[61,74],"been":[62,75],"refined,":[63],"combination":[66],"of":[67,97,127],"existing":[72],"changed":[76],"from":[77],"MED+MPD":[79],"MED+MRD":[82],"structure.":[83],"Experiments":[84],"with":[85],"various":[86],"combinations,":[88],"including":[89],"MSD+MED,":[90],"MSD+MRD,":[91],"MPD+MED+MRD,":[93],"validate":[94],"effectiveness":[96],"BemaGANv2.":[98],"The":[99],"final":[100],"serves":[103],"a":[105],"vocoder":[106],"Text-to-Audio":[108],"(TTA)":[109],"or":[110],"Text-to-Music":[111],"(TTM)":[112],"tasks":[113],"restore":[115],"original":[117],"audio,":[118],"aiming":[119],"enhance":[121],"fidelity":[123],"perceptual":[125],"quality":[126],"generated":[128],"audio.":[130],"Experimental":[131],"results":[132],"demonstrate":[133],"that":[134],"outperforms":[136],"previous":[138],"both":[141],"objective":[142],"subjective":[144],"evaluation":[145],"metrics,":[146],"making":[147],"it":[148],"suitable":[150],"for":[151],"generation.":[154]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
