{"id":"https://openalex.org/W4406858552","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848766","title":"Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model","display_name":"Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858552","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848766"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5109692719","display_name":"Joonyong Park","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Joonyong Park","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010715755","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3012-1607"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7675999999046326,"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":0.7675999999046326,"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/computer-science","display_name":"Computer science","score":0.7866994738578796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.584374725818634},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49124211072921753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48603683710098267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45799121260643005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866994738578796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.584374725818634},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49124211072921753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48603683710098267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45799121260643005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":[{"id":"https://openalex.org/G4346272346","display_name":"Measurement of L2 pronunciation deviation and L2 listening disfluency and its application to prosody training for smooth international communication","funder_award_id":"23K17459","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8512205465","display_name":"Measurement and modeling of cognitive breakdown and their use to enhance cognitive robustness for international oral communication","funder_award_id":"22H00527","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2842511635","https://openalex.org/W2964243274","https://openalex.org/W3015877095","https://openalex.org/W3093096176","https://openalex.org/W3196027980","https://openalex.org/W3197259906","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4224932952","https://openalex.org/W4292264739","https://openalex.org/W4295308567","https://openalex.org/W4296068791","https://openalex.org/W4372349107","https://openalex.org/W4385245566","https://openalex.org/W4385822372","https://openalex.org/W6745289305","https://openalex.org/W6767245602","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783726357","https://openalex.org/W6790356757","https://openalex.org/W6796464841","https://openalex.org/W6811170316","https://openalex.org/W6839738141"],"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/W3204019825"],"abstract_inverted_index":{"We":[0],"examine":[1],"the":[2,18,22,59,70,82],"text-free":[3],"speech":[4,20,37,44,48,56,61,84],"representations":[5,24,38,45,68,96,107],"of":[6,26,81],"raw":[7,31],"audio":[8,32],"obtained":[9],"from":[10,46,69],"a":[11],"self-supervised":[12],"learning":[13],"(SSL)":[14],"model":[15,72],"by":[16],"analyzing":[17],"synthesized":[19,83],"using":[21,65,94,104],"SSL":[23,71],"instead":[25],"conventional":[27],"text":[28,76,95],"representations.":[29],"Since":[30],"does":[33],"not":[34],"have":[35,85],"paired":[36],"as":[39],"transcribed":[40],"texts":[41],"do,":[42],"obtaining":[43],"unpaired":[47],"is":[49,63,97,108],"crucial":[50],"for":[51,55,99,110],"augmenting":[52],"available":[53],"datasets":[54],"synthesis.":[57],"Specifically,":[58],"proposed":[60],"synthesis":[62],"conducted":[64],"discrete":[66,105],"symbol":[67,106],"in":[73],"comparison":[74],"with":[75],"representations,":[77],"and":[78,116],"analytical":[79],"examinations":[80],"been":[86],"carried":[87],"out.":[88],"The":[89],"results":[90],"empirically":[91],"show":[92],"that":[93],"advantageous":[98],"preserving":[100,111],"semantic":[101],"information,":[102],"while":[103],"superior":[109],"acoustic":[112],"content,":[113],"including":[114],"prosodic":[115],"intonational":[117],"information.":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}