{"id":"https://openalex.org/W4403662013","doi":"https://doi.org/10.48550/arxiv.2409.08680","title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","display_name":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4403662013","doi":"https://doi.org/10.48550/arxiv.2409.08680"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.08680","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08680","pdf_url":"https://arxiv.org/pdf/2409.08680","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.08680","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027728339","display_name":"Minglun Han","orcid":"https://orcid.org/0000-0002-5120-069X","observed_orcids":["https://orcid.org/0000-0002-5120-069X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Minglun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102945873","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5680-433X","observed_orcids":["https://orcid.org/0000-0001-5680-433X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shen, Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101394624","display_name":"Youjia Huang","orcid":"https://orcid.org/0009-0003-2491-4958","observed_orcids":["https://orcid.org/0009-0003-2491-4958"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Youjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067488078","display_name":"Mingkun Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Mingkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101394625","display_name":"Zehua Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zehua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000236213","display_name":"Linhao Dong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Linhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115592661","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0008-8573-2839","observed_orcids":["https://orcid.org/0009-0008-8573-2839","https://orcid.org/0009-0002-3577-8261","https://orcid.org/0009-0009-4061-6364"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.000699999975040555,"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/next-token-prediction","display_name":"next-token prediction","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7821732759475708},{"id":"https://openalex.org/C152630561","wikidata":"https://www.wikidata.org/wiki/Q6997750","display_name":"Nest (protein structural motif)","level":2,"score":0.7058422565460205},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6631499528884888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4823417365550995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37423330545425415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3494577407836914},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3290514051914215},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16965320706367493},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13142293691635132},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11488544940948486},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.08680","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08680","pdf_url":"https://arxiv.org/pdf/2409.08680","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.08680","doi":"https://doi.org/10.48550/arxiv.2409.08680","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.08680","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.08680","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08680","pdf_url":"https://arxiv.org/pdf/2409.08680","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403662013.pdf","grobid_xml":"https://content.openalex.org/works/W4403662013.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W1974219284","https://openalex.org/W2997152889","https://openalex.org/W2315260587"],"abstract_inverted_index":{"Speech":[0],"self-supervised":[1,13],"pre-training":[2,52],"can":[3],"effectively":[4],"improve":[5],"the":[6,46,73,77,83,109,116,122,126,130,133,136],"performance":[7,88,97],"of":[8,108,113,119,125,135],"downstream":[9,37],"tasks.":[10],"However,":[11],"previous":[12],"learning":[14],"(SSL)":[15],"methods":[16],"for":[17,36,147],"speech,":[18],"such":[19],"as":[20,72],"HuBERT":[21],"and":[22,32,66,95,121,141,145],"BEST-RQ,":[23,82],"focus":[24],"on":[25,89,98],"utilizing":[26],"non-causal":[27],"encoders":[28,61],"with":[29,54,62],"bidirectional":[30],"context,":[31],"lack":[33],"sufficient":[34],"support":[35],"streaming":[38,99,114],"models.":[39],"To":[40],"address":[41],"this":[42],"issue,":[43],"we":[44],"introduce":[45],"next":[47,68],"token":[48,69],"prediction":[49,70],"based":[50],"speech":[51,92,139,148],"method":[53],"random-projection":[55],"quantizer":[56],"(NEST-RQ).":[57],"NEST-RQ":[58,85],"employs":[59],"causal":[60],"only":[63],"left":[64],"context":[65,111],"uses":[67],"(NTP)":[71],"training":[74],"task.":[75],"On":[76],"large-scale":[78],"dataset,":[79],"compared":[80],"to":[81],"proposed":[84],"achieves":[86],"comparable":[87],"non-streaming":[90],"automatic":[91],"recognition":[93],"(ASR)":[94],"better":[96],"ASR.":[100],"We":[101],"also":[102],"conduct":[103],"analytical":[104],"experiments":[105],"in":[106,138],"terms":[107],"future":[110],"size":[112,124],"ASR,":[115],"codebook":[117],"quality":[118],"SSL":[120,140,149],"model":[123],"encoder.":[127],"In":[128],"summary,":[129],"paper":[131],"demonstrates":[132],"feasibility":[134],"NTP":[137],"provides":[142],"empirical":[143],"evidence":[144],"insights":[146],"research.":[150]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}