{"id":"https://openalex.org/W4307464713","doi":"https://doi.org/10.48550/arxiv.2203.15952","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","display_name":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W4307464713","doi":"https://doi.org/10.48550/arxiv.2203.15952"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.15952","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15952","pdf_url":"https://arxiv.org/pdf/2203.15952","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,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.15952","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058886181","display_name":"Shaojin Ding","orcid":"https://orcid.org/0000-0002-2108-3111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Shaojin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007839762","display_name":"Phoenix Meadowlark\u200e","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meadowlark, Phoenix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153566","display_name":"Yanzhang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yanzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104269404","display_name":"\u0141ukasz Lew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lew, Lukasz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033596864","display_name":"Shivani Agrawal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agrawal, Shivani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070398306","display_name":"Oleg Rybakov\u200e","orcid":"https://orcid.org/0000-0003-4805-3083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rybakov, Oleg","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":0.9986000061035156,"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":0.9986000061035156,"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":0.9912999868392944,"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/T10860","display_name":"Speech and Audio Processing","score":0.9898999929428101,"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/quantization","display_name":"Quantization (signal processing)","score":0.8538599014282227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7278809547424316},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5965206027030945},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5696263313293457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5490647554397583},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5395050048828125},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4337320029735565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36811864376068115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3670726418495178},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32290518283843994},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3006132245063782}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8538599014282227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278809547424316},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5965206027030945},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5696263313293457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5490647554397583},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5395050048828125},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4337320029735565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36811864376068115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3670726418495178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32290518283843994},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3006132245063782}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.15952","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15952","pdf_url":"https://arxiv.org/pdf/2203.15952","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,"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.2203.15952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.15952","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,"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:2203.15952","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15952","pdf_url":"https://arxiv.org/pdf/2203.15952","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,"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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307464713.pdf","grobid_xml":"https://content.openalex.org/works/W4307464713.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2057878850","https://openalex.org/W2169871401","https://openalex.org/W3008492011"],"abstract_inverted_index":{"Reducing":[0],"the":[1,42,107,119,135,142,148,184],"latency":[2],"and":[3,36,87,115,122,146,164,174],"model":[4,24,128,170],"size":[5,131,180],"has":[6,26,178],"always":[7],"been":[8],"a":[9,53,124,154,166],"significant":[10],"research":[11],"problem":[12],"for":[13,112,141],"live":[14],"Automatic":[15],"Speech":[16],"Recognition":[17],"(ASR)":[18],"application":[19],"scenarios.":[20],"Along":[21],"this":[22,63],"direction,":[23],"quantization":[25,74,102,117,152],"become":[27],"an":[28],"increasingly":[29],"popular":[30],"approach":[31],"to":[32,67,82,98,134,183],"compress":[33],"neural":[34],"networks":[35],"reduce":[37],"computation":[38],"cost.":[39],"Most":[40],"of":[41,109,150],"existing":[43],"practical":[44,155],"ASR":[45,70,96,156,169],"systems":[46],"apply":[47],"post-training":[48],"8-bit":[49,175],"quantization.":[50],"To":[51],"achieve":[52],"higher":[54],"compression":[55],"rate":[56],"without":[57],"introducing":[58],"additional":[59],"performance":[60],"regression,":[61],"in":[62],"study,":[64],"we":[65,105,140],"propose":[66],"develop":[68],"4-bit":[69,126,151,173],"models":[71,97],"with":[72,129,161,171],"native":[73,79],"aware":[75],"training,":[76],"which":[77],"leverages":[78],"integer":[80],"operations":[81],"effectively":[83],"optimize":[84],"both":[85,113],"training":[86],"inference.":[88],"We":[89],"conducted":[90],"two":[91],"experiments":[92],"on":[93,118,153],"state-of-the-art":[94],"Conformer-based":[95],"evaluate":[99],"our":[100],"proposed":[101],"technique.":[103],"First,":[104],"explored":[106],"impact":[108],"different":[110],"precisions":[111],"weight":[114],"activation":[116],"LibriSpeech":[120],"dataset,":[121],"obtained":[123],"lossless":[125,167],"Conformer":[127,168],"5.8x":[130],"reduction":[132,181],"compared":[133,182],"float32":[136,185],"model.":[137,186],"Following":[138],"this,":[139],"first":[143],"time":[144],"investigated":[145],"revealed":[147],"viability":[149],"system":[157],"that":[158,177],"is":[159],"trained":[160],"large-scale":[162],"datasets,":[163],"produced":[165],"mixed":[172],"weights":[176],"5x":[179]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2022-11-01T00:00:00"}