{"id":"https://openalex.org/W4406859264","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849090","title":"NecoBERT: Self-Supervised Learning Model Trained by Masked Language Modeling on Rich Acoustic Features Derived from Neural Audio Codec","display_name":"NecoBERT: Self-Supervised Learning Model Trained by Masked Language Modeling on Rich Acoustic Features Derived from Neural Audio Codec","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859264","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849090"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849090","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":"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/A5068962900","display_name":"Wataru Nakata","orcid":"https://orcid.org/0000-0003-3953-6534"},"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":true,"raw_author_name":"Wataru Nakata","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"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":"Takaaki Saeki","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"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":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"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":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068962900"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24366685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8478999733924866,"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":0.8478999733924866,"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":0.8105752468109131},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.8063241243362427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.69268399477005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47268348932266235},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4622160792350769},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.441182017326355},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2474624216556549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105752468109131},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8063241243362427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.69268399477005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47268348932266235},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4622160792350769},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.441182017326355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2474624216556549},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849090","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":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2107860279","https://openalex.org/W2131738223","https://openalex.org/W2471520273","https://openalex.org/W2890964092","https://openalex.org/W2903739847","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3011411500","https://openalex.org/W3015780049","https://openalex.org/W3161695192","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4226033575","https://openalex.org/W4307323391","https://openalex.org/W4307680525","https://openalex.org/W4381786045","https://openalex.org/W4385822381","https://openalex.org/W4385823338","https://openalex.org/W4391021682","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6844194202","https://openalex.org/W6848735303","https://openalex.org/W6853515095","https://openalex.org/W6861267420"],"related_works":["https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481","https://openalex.org/W2120730869","https://openalex.org/W1911859126"],"abstract_inverted_index":{"We":[0,93],"propose":[1],"NecoBERT,":[2],"a":[3],"self-supervised":[4],"learning":[5],"(SSL)":[6],"model":[7],"to":[8,76,87],"extract":[9],"speech":[10,22,37,105,129],"features":[11,58,86],"containing":[12],"semantic":[13,52,89],"and":[14,27,104,128],"acoustic":[15,54,81,85],"information.":[16],"Unsupervisedly":[17],"learned":[18,57],"representations":[19],"using":[20],"massive":[21],"data,":[23],"such":[24],"as":[25,91],"SSL":[26],"neural":[28],"audio":[29],"codec":[30],"(NAC)":[31],"features,":[32,82],"are":[33,59],"essential":[34],"for":[35,63],"developing":[36],"foundation":[38],"models.":[39],"However,":[40],"because":[41],"conventional":[42],"methods":[43],"typically":[44],"capture":[45],"one":[46],"specific":[47],"aspect":[48],"of":[49],"speech,":[50],"i.e.,":[51],"or":[53],"information,":[55],"the":[56,84,101],"not":[60,115],"always":[61],"suitable":[62],"complicated":[64],"downstream":[65],"tasks.":[66,107],"NecoBERT":[67,95,113],"addresses":[68],"this":[69],"issue":[70],"by":[71],"masked":[72],"language":[73],"modeling":[74],"similar":[75],"HuBERT":[77,117],"on":[78,96],"NAC-derived":[79],"rich":[80],"enabling":[83],"represent":[88],"information":[90],"well.":[92],"evaluate":[94],"recognition":[97,120],"tasks":[98],"taken":[99],"from":[100],"SUPERB":[102],"benchmark":[103],"resynthesis":[106],"The":[108],"results":[109],"show":[110],"that":[111],"although":[112],"does":[114],"outperform":[116],"in":[118,125],"some":[119],"tasks,":[121],"it":[122],"performs":[123],"superiorly":[124],"speaker":[126],"verification":[127],"resynthesis.":[130]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}