{"id":"https://openalex.org/W4416799177","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249203","title":"ULF-TTS: An Uncluttered Hybrid TTS System Using Language and Flow Matching Models","display_name":"ULF-TTS: An Uncluttered Hybrid TTS System Using Language and Flow Matching Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799177","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249203"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249203","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/A5100369517","display_name":"Jae Hyun Park","orcid":"https://orcid.org/0000-0001-6352-2162"},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jae Hyun Park","raw_affiliation_strings":["NC AI Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NC AI Co., Ltd","institution_ids":["https://openalex.org/I114129787"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Seung Jae Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung Jae Choi","raw_affiliation_strings":["NC AI Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NC AI Co., Ltd","institution_ids":["https://openalex.org/I114129787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120437496","display_name":"Young Sik Eom","orcid":null},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young Sik Eom","raw_affiliation_strings":["NC AI Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NC AI Co., Ltd","institution_ids":["https://openalex.org/I114129787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120525826","display_name":"Allison Shindell","orcid":null},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allison Shindell","raw_affiliation_strings":["NC AI Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NC AI Co., Ltd","institution_ids":["https://openalex.org/I114129787"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Min-Gwan Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min-Gwan Seo","raw_affiliation_strings":["NC AI Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NC AI Co., Ltd","institution_ids":["https://openalex.org/I114129787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000172890","display_name":"G. W. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I114129787","display_name":"NCR (United States)","ror":"https://ror.org/00nqjkj48","country_code":"US","type":"company","lineage":["https://openalex.org/I114129787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gyeong-Hoon Lee","raw_affiliation_strings":["NC AI Co., Ltd"],"affiliations":[{"raw_affiliation_string":"NC AI Co., Ltd","institution_ids":["https://openalex.org/I114129787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100369517"],"corresponding_institution_ids":["https://openalex.org/I114129787"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19111914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"962","last_page":"967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8105000257492065,"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":0.8105000257492065,"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":0.09040000289678574,"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":0.02370000071823597,"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/leverage","display_name":"Leverage (statistics)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5189999938011169},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.41339999437332153},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.3815999925136566},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.35040000081062317},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34439998865127563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860000133514404},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4440000057220459},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3490999937057495},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249203","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3013020904","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4252812408","https://openalex.org/W4381786045","https://openalex.org/W4382202681","https://openalex.org/W4385823191","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4392931276","https://openalex.org/W4402111255","https://openalex.org/W4406461672","https://openalex.org/W4406495593","https://openalex.org/W4412945617"],"related_works":[],"abstract_inverted_index":{"Hybrid":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3,27,101],"that":[4,49,90],"integrate":[5],"a":[6,51,66,70],"language":[7,75],"model":[8,76],"with":[9],"flow":[10,53],"matching":[11,54],"decoders":[12],"have":[13],"been":[14],"proposed":[15,92],"to":[16,77],"generate":[17],"speech":[18,105],"in":[19],"voice-related":[20],"applications":[21],"such":[22],"as":[23],"dubbing.":[24],"However,":[25],"these":[26],"suffer":[28],"from":[29,69],"latency":[30],"and":[31,38,56,86],"computational":[32],"overhead":[33],"caused":[34],"by":[35],"next-token":[36],"prediction":[37,60],"denoising":[39],"steps.":[40],"Therefore,":[41],"we":[42,64],"propose":[43],"an":[44],"uncluttered":[45],"hybrid":[46,100],"TTS":[47],"system":[48],"integrates":[50],"lightweight":[52],"decoder":[55],"supports":[57],"variable":[58],"token":[59],"time.":[61],"In":[62],"addition,":[63],"leverage":[65],"training":[67],"strategy":[68],"diffusion-based":[71],"approach":[72],"into":[73],"the":[74],"enhance":[78],"its":[79],"generative":[80],"performance.":[81],"The":[82],"results":[83],"of":[84],"objective":[85],"subjective":[87],"evaluations":[88],"demonstrate":[89],"our":[91],"method":[93],"is":[94,109],"significantly":[95],"more":[96],"efficient":[97],"than":[98],"existing":[99],"while":[102],"maintaining":[103],"competitive":[104],"quality.":[106],"Online":[107],"demo":[108],"available":[110],"at":[111],"https://nc-ai.github.io/speech/publications/ulftts/index.html.":[112]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}