{"id":"https://openalex.org/W4224919682","doi":"https://doi.org/10.1109/icassp43922.2022.9747842","title":"Bilingual End-to-End ASR with Byte-Level Subwords","display_name":"Bilingual End-to-End ASR with Byte-Level Subwords","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919682","doi":"https://doi.org/10.1109/icassp43922.2022.9747842"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747842","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"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/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":false,"raw_author_name":"Roger Hsiao","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"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":"Arnab Ghoshal","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108296148"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.6243,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65899908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6417","last_page":"6421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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":0.7972896099090576},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7400761842727661},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6841370463371277},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.6154386401176453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5944636464118958},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5765170454978943},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4768292009830475},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4638649821281433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42008188366889954},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09950608015060425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972896099090576},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7400761842727661},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6841370463371277},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.6154386401176453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5944636464118958},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5765170454978943},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4768292009830475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4638649821281433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42008188366889954},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09950608015060425},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747842","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2327501763","https://openalex.org/W2757141711","https://openalex.org/W2786835190","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2962784628","https://openalex.org/W2963208801","https://openalex.org/W2963850025","https://openalex.org/W2963939538","https://openalex.org/W2964002616","https://openalex.org/W2971840980","https://openalex.org/W2998353611","https://openalex.org/W3048407879","https://openalex.org/W3094957294","https://openalex.org/W3096032230","https://openalex.org/W3097961301","https://openalex.org/W3137976833","https://openalex.org/W3164045210","https://openalex.org/W4287726212","https://openalex.org/W6748640972","https://openalex.org/W6780612146","https://openalex.org/W6796054912"],"related_works":["https://openalex.org/W2353325398","https://openalex.org/W2558599680","https://openalex.org/W2367608902","https://openalex.org/W2359823483","https://openalex.org/W2392667367","https://openalex.org/W2381559703","https://openalex.org/W2353027778","https://openalex.org/W2381835873","https://openalex.org/W2947571721","https://openalex.org/W1565952126"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,86],"investigate":[4],"how":[5],"the":[6],"output":[7],"representation":[8],"of":[9,108],"an":[10],"end-to-end":[11,50],"neural":[12],"network":[13],"affects":[14],"multilingual":[15,123],"automatic":[16],"speech":[17],"recognition":[18],"(ASR).":[19],"We":[20,44,75,113],"study":[21],"different":[22],"representations":[23],"including":[24],"character-level,":[25],"byte-level,":[26],"byte":[27,33],"pair":[28,34],"encoding":[29,35],"(BPE),":[30],"and":[31,38,42,81,85,110],"byte-level":[32],"(BBPE)":[36],"representations,":[37],"analyze":[39],"their":[40],"strengths":[41],"weaknesses.":[43],"focus":[45],"on":[46,79],"developing":[47],"a":[48,66],"single":[49,67],"model":[51],"to":[52,101],"support":[53],"utterance-based":[54,95],"bilingual":[55,96],"ASR,":[56],"where":[57],"speakers":[58],"do":[59],"not":[60],"alternate":[61],"between":[62],"two":[63],"languages":[64,72],"in":[65],"utterance":[68],"but":[69],"may":[70],"change":[71],"across":[73],"utterances.":[74],"conduct":[76],"our":[77],"experiments":[78],"English":[80],"Mandarin":[82],"dictation":[83],"tasks,":[84],"find":[87],"that":[88,117],"BBPE":[89],"with":[90,105,115],"penalty":[91],"schemes":[92],"can":[93],"improve":[94],"ASR":[97],"performance":[98],"by":[99],"2%":[100],"5%":[102],"relative":[103],"even":[104],"smaller":[106],"number":[107],"outputs":[109],"fewer":[111],"parameters.":[112],"conclude":[114],"analysis":[116],"indicates":[118],"directions":[119],"for":[120],"further":[121],"improving":[122],"ASR.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
