{"id":"https://openalex.org/W4406461475","doi":"https://doi.org/10.1109/slt61566.2024.10832325","title":"Self-Supervised Syllable Discovery Based on Speaker-Disentangled Hubert","display_name":"Self-Supervised Syllable Discovery Based on Speaker-Disentangled Hubert","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461475","doi":"https://doi.org/10.1109/slt61566.2024.10832325"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5036072183","display_name":"Ryota Komatsu","orcid":"https://orcid.org/0000-0002-6139-0642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryota Komatsu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9907000064849854,"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/T11309","display_name":"Music and Audio Processing","score":0.9883000254631042,"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/syllable","display_name":"Syllable","score":0.7609137296676636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7427436709403992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6012833118438721},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5286489129066467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46715468168258667}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7609137296676636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427436709403992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6012833118438721},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5286489129066467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46715468168258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W1494198834","https://openalex.org/W1836465849","https://openalex.org/W2118612506","https://openalex.org/W2726515241","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2908510526","https://openalex.org/W3140429000","https://openalex.org/W3159481202","https://openalex.org/W3209059054","https://openalex.org/W4224875474","https://openalex.org/W4281789500","https://openalex.org/W4283659485","https://openalex.org/W4287854499","https://openalex.org/W4301371414","https://openalex.org/W4372348373","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385822740","https://openalex.org/W4385823059","https://openalex.org/W4385823277","https://openalex.org/W4389524500","https://openalex.org/W4392904409","https://openalex.org/W4394671563","https://openalex.org/W4394773771","https://openalex.org/W4398157616","https://openalex.org/W4401610816","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6790356757","https://openalex.org/W6803547063","https://openalex.org/W6838789019","https://openalex.org/W6839738141","https://openalex.org/W6867926528"],"related_works":["https://openalex.org/W2514064218","https://openalex.org/W2094188777","https://openalex.org/W2132658536","https://openalex.org/W2112609279","https://openalex.org/W1581825163","https://openalex.org/W1483316057","https://openalex.org/W3204019825","https://openalex.org/W2366310385","https://openalex.org/W2399404538","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,51,67],"representation":[2,63],"learning":[3],"has":[4],"become":[5],"essential":[6],"for":[7],"extracting":[8],"meaningful":[9],"features":[10,25,69],"from":[11,23,55,66,112,134],"untranscribed":[12],"audio.":[13],"Recent":[14],"advances":[15],"highlight":[16],"the":[17,24,42,82,86,131,145],"potential":[18],"of":[19,41],"deriving":[20],"discrete":[21],"symbols":[22],"correlated":[26],"with":[27,91,95],"linguistic":[28,96],"units,":[29],"which":[30],"enables":[31],"text-less":[32],"training":[33,127],"across":[34],"diverse":[35],"tasks.":[36],"In":[37,60],"particular,":[38],"sentence-level":[39,62],"Self-Distillation":[40],"pretrained":[43],"HuBERT":[44],"(SD-HuBERT)":[45],"induces":[46],"syllabic":[47,110,154,165],"structures":[48],"within":[49,167],"latent":[50],"frame":[52,68],"representations":[53],"extracted":[54],"an":[56],"intermediate":[57],"Transformer":[58],"layer.":[59],"SD-HuBERT,":[61],"is":[64],"accumulated":[65],"through":[70],"self-attention":[71],"layers":[72],"using":[73],"a":[74,103,125],"special":[75],"CLS":[76,87,132],"token.":[77],"However,":[78],"we":[79,101],"observe":[80],"that":[81,108,141],"information":[83],"aggregated":[84],"in":[85,149,163],"token":[88,133],"correlates":[89],"more":[90],"speaker":[92,113,118],"identity":[93],"than":[94],"content.":[97],"To":[98],"address":[99],"this,":[100],"propose":[102],"speech-only":[104,168],"self-supervised":[105],"fine-tuning":[106],"approach":[107,143],"separates":[109],"units":[111],"information.":[114,137],"Our":[115],"method":[116,148],"introduces":[117],"perturbation":[119],"as":[120],"data":[121],"augmentation":[122],"and":[123,153,174],"adopts":[124],"frame-level":[126],"objective":[128],"to":[129],"prevent":[130],"aggregating":[135],"paralinguistic":[136],"Experimental":[138],"results":[139],"show":[140],"our":[142],"surpasses":[144],"current":[146],"state-of-the-art":[147],"most":[150],"syllable":[151],"segmentation":[152],"unit":[155],"quality":[156],"metrics":[157],"on":[158],"Librispeech,":[159],"underscoring":[160],"its":[161],"effectiveness":[162],"promoting":[164],"organization":[166],"models<sup":[169],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[170,172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.<sup":[171],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Codes":[173],"models:https://github.com/ryota-komatsu/speaker_disentangled_hubert":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
