{"id":"https://openalex.org/W4406461961","doi":"https://doi.org/10.1109/slt61566.2024.10832272","title":"Optimizing Byte-Level Representation For End-To-End ASR","display_name":"Optimizing Byte-Level Representation For End-To-End ASR","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461961","doi":"https://doi.org/10.1109/slt61566.2024.10832272"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832272","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":"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/A5033764781","display_name":"Roger Hsiao","orcid":"https://orcid.org/0000-0001-8638-4508"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Roger Hsiao","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108296148","display_name":"Liuhui Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liuhui Deng","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079853614","display_name":"Ruchir Travadi","orcid":"https://orcid.org/0000-0002-1272-5282"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruchir Travadi","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033764781"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.9534,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77880437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"462","last_page":"467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9968000054359436,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.996399998664856,"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":0.7490079998970032},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.6865143179893494},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6807723045349121},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5120783448219299},{"id":"https://openalex.org/keywords/end-user-development","display_name":"End-user development","score":0.4149889051914215},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.3561970889568329},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26767897605895996},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2173750102519989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19998398423194885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490079998970032},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.6865143179893494},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6807723045349121},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5120783448219299},{"id":"https://openalex.org/C2776867947","wikidata":"https://www.wikidata.org/wiki/Q500467","display_name":"End-user development","level":3,"score":0.4149889051914215},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.3561970889568329},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26767897605895996},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2173750102519989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19998398423194885},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832272","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2127141656","https://openalex.org/W2531409750","https://openalex.org/W2752796333","https://openalex.org/W2757141711","https://openalex.org/W2962784628","https://openalex.org/W2963208801","https://openalex.org/W2963799213","https://openalex.org/W2964002616","https://openalex.org/W2998353611","https://openalex.org/W3097777922","https://openalex.org/W3164045210","https://openalex.org/W3197478142","https://openalex.org/W4224919682","https://openalex.org/W4312974539","https://openalex.org/W6748381668","https://openalex.org/W6847363464","https://openalex.org/W6852843773"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W3163634122","https://openalex.org/W2113114423","https://openalex.org/W4287122814","https://openalex.org/W4391709660","https://openalex.org/W2529145526","https://openalex.org/W2884814595","https://openalex.org/W4327633437","https://openalex.org/W4396816926","https://openalex.org/W4393212338"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,7,60,91,123],"novel":[3],"approach":[4,130],"to":[5,48,73],"optimizing":[6],"byte-level":[8,63,92],"representation":[9,17,43,64,93,134],"for":[10,65,94],"end-to-end":[11],"automatic":[12],"speech":[13],"recognition":[14],"(ASR).":[15],"Byte-level":[16],"is":[18,35,59,70],"often":[19],"used":[20,62],"by":[21,135],"large":[22],"scale":[23],"multilingual":[24,66],"ASR":[25,46,95,125],"systems":[26],"when":[27],"the":[28,32,45],"character":[29],"set":[30],"of":[31,41],"supported":[33],"languages":[34],"large.":[36],"The":[37],"compactness":[38],"and":[39,53,82,96,109],"universality":[40],"bytelevel":[42],"allow":[44],"models":[47],"use":[49],"smaller":[50],"output":[51],"vocabularies":[52],"therefore,":[54],"provide":[55],"more":[56],"flexibility.":[57],"UTF8":[58],"commonly":[61],"ASR,":[67],"but":[68],"it":[69],"not":[71],"designed":[72],"optimize":[74,90],"machine":[75],"learning":[76],"tasks":[77],"directly.":[78],"By":[79],"using":[80],"auto-encoder":[81],"vector":[83],"quantization,":[84],"we":[85,88,120],"show":[86,121],"that":[87,122],"can":[89,103,131],"achieve":[97],"better":[98],"accuracy.":[99],"Our":[100],"proposed":[101],"framework":[102],"incorporate":[104],"information":[105],"from":[106],"different":[107],"modalities,":[108],"provides":[110],"an":[111,116],"error":[112,139],"correction":[113],"mechanism.":[114],"In":[115],"English/Mandarin":[117],"dictation":[118],"task,":[119],"bilingual":[124],"model":[126],"built":[127],"with":[128],"this":[129],"outperform":[132],"UTF-8":[133],"5%":[136],"relative":[137],"in":[138],"rate.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}