{"id":"https://openalex.org/W4210756942","doi":"https://doi.org/10.1109/asru51503.2021.9687943","title":"HiTNet: Byte-to-BPE Hierarchical Transcription Network for End-to-End Speech Recognition","display_name":"HiTNet: Byte-to-BPE Hierarchical Transcription Network for End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210756942","doi":"https://doi.org/10.1109/asru51503.2021.9687943"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687943","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043920881","display_name":"Abhinav Garg","orcid":"https://orcid.org/0000-0001-5082-5500"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Abhinav Garg","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396580","display_name":"Jiyeon Kim","orcid":"https://orcid.org/0000-0001-7964-5060"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiyeon Kim","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065995328","display_name":"Mehul Kumar","orcid":"https://orcid.org/0000-0001-7341-2362"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mehul Kumar","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072672307","display_name":"Sachin Singh","orcid":"https://orcid.org/0000-0003-2788-5462"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sachin Singh","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079400687","display_name":"Ashutosh Gupta","orcid":"https://orcid.org/0000-0002-3768-6355"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ashutosh Gupta","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056592130","display_name":"Ankur Kumar","orcid":"https://orcid.org/0000-0002-7686-7335"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ankur Kumar","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067313233","display_name":"Nauman Dawalatabad","orcid":"https://orcid.org/0000-0003-1592-6300"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nauman Dawalatabad","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038271343","display_name":"Aman Maghan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Aman Maghan","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079810318","display_name":"Shatrughan Singh","orcid":"https://orcid.org/0000-0003-3758-3214"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shatrughan Singh","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5113125574"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22228454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1810 1398","issue":null,"first_page":"395","last_page":"402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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/byte","display_name":"Byte","score":0.9149916172027588},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.9043013453483582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081572651863098},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.687002420425415},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4537421464920044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4309820830821991},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42775267362594604},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.40449434518814087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3419375717639923},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1314600706100464},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12460502982139587},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09400677680969238}],"concepts":[{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.9149916172027588},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.9043013453483582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081572651863098},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.687002420425415},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4537421464920044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4309820830821991},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42775267362594604},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.40449434518814087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3419375717639923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1314600706100464},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12460502982139587},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09400677680969238},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687943","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2470673105","https://openalex.org/W2603679025","https://openalex.org/W2799800213","https://openalex.org/W2888884590","https://openalex.org/W2914913241","https://openalex.org/W2932675979","https://openalex.org/W2936774411","https://openalex.org/W2962742956","https://openalex.org/W2962824709","https://openalex.org/W2962961016","https://openalex.org/W2963414781","https://openalex.org/W2964002616","https://openalex.org/W2972426539","https://openalex.org/W2972816482","https://openalex.org/W2973122799","https://openalex.org/W2997454826","https://openalex.org/W3007528493","https://openalex.org/W3008587939","https://openalex.org/W3011339933","https://openalex.org/W3094721881","https://openalex.org/W3095193086","https://openalex.org/W3095867028","https://openalex.org/W3096758108","https://openalex.org/W3162308011","https://openalex.org/W3162638900","https://openalex.org/W3168770049","https://openalex.org/W4289440825","https://openalex.org/W6623517193","https://openalex.org/W6747398299","https://openalex.org/W6754576867"],"related_works":["https://openalex.org/W2544616823","https://openalex.org/W1982067419","https://openalex.org/W1967913462","https://openalex.org/W2355552759","https://openalex.org/W1993624831","https://openalex.org/W4210756942","https://openalex.org/W3139199132","https://openalex.org/W2996640127","https://openalex.org/W1769898127","https://openalex.org/W2155299007"],"abstract_inverted_index":{"In":[0,46],"this":[1,48],"paper,":[2],"we":[3],"propose":[4],"a":[5,163],"new":[6],"byte":[7,183,190],"to":[8,53,65,70,76,125,188],"byte-pair-encoding":[9],"(BPE)":[10],"Hierarchical":[11],"Transcription":[12],"Network":[13],"(HiTNet)":[14],"architecture":[15,26,131,173],"for":[16],"end-to-end":[17],"(e2e)":[18],"automatic":[19],"speech":[20],"recognition":[21],"(ASR).":[22],"The":[23,103,129],"proposed":[24,130,172],"HiTNet":[25],"simultaneously":[27],"encodes":[28],"as":[29,31,42],"well":[30],"decodes":[32,133],"information":[33,90,105,118,134,142,157],"hierarchically":[34,154],"at":[35,100,106,120,143,148,158],"different":[36],"levels":[37,55],"of":[38,56,180],"linguistic":[39,98,141],"granularity":[40,57],"such":[41],"bytes":[43,63],"and":[44,78,184,191],"BPE.":[45],"general":[47],"idea":[49],"can":[50],"be":[51],"extended":[52],"any":[54],"including":[58],"phonemes":[59],"or":[60,62,72,112],"graphemes":[61],"(character":[64],"sub-character":[66],"in":[67,91,135],"some":[68],"languages),":[69],"sub-words":[71],"byte-pair":[73],"encodings":[74],"(BPE),":[75],"words,":[77],"so":[79],"on.":[80],"Existing":[81],"hierarchical":[82,93,137,167],"e2e":[83],"ASR":[84],"models":[85],"primarily":[86,132],"encode":[87],"the":[88,117,126,140,149,153,171,176,182],"acoustic":[89,156],"an":[92,136],"manner":[94,138],"governed":[95],"by":[96],"weaker":[97],"constraints":[99],"each":[101,107,121,144,159],"level.":[102,160],"language":[104],"level":[108,122,145],"is":[109,116],"neither":[110],"embedded":[111],"used":[113],"explicitly,":[114,146],"nor":[115],"decoded":[119],"passed":[123],"on":[124],"next":[127],"stage.":[128],"utilizing":[139,152],"while":[147],"same":[150],"time":[151],"encoded":[155],"Experiments":[161],"with":[162],"two-level":[164],"byte-to-BPE":[165],"(b2B)":[166],"transcription":[168],"show":[169],"that":[170],"significantly":[174],"reduces":[175],"word":[177],"error":[178],"rates":[179],"both":[181],"BPE":[185,192],"decoders":[186],"compared":[187],"baseline":[189],"based":[193],"attention":[194],"encoder-decoder":[195],"models.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
