{"id":"https://openalex.org/W4372190173","doi":"https://doi.org/10.1109/icassp49357.2023.10096812","title":"Investigation into Phone-Based Subword Units for Multilingual End-to-End Speech Recognition","display_name":"Investigation into Phone-Based Subword Units for Multilingual End-to-End Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372190173","doi":"https://doi.org/10.1109/icassp49357.2023.10096812"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040785062","display_name":"Saierdaer Yusuyin","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Saierdaer Yusuyin","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757355","display_name":"Hao Huang","orcid":"https://orcid.org/0009-0005-7353-3072"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China","Xinjiang Key Laboratory of Multi-Lingual Information Technology, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741943","display_name":"Junhua Liu","orcid":"https://orcid.org/0000-0003-4477-7439"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhua Liu","raw_affiliation_strings":["iFlyTek,Hefei,China","iFlyTek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlyTek,Hefei,China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlyTek, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331555","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0001-8624-4126"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["iFlyTek,Hefei,China","iFlyTek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlyTek,Hefei,China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlyTek, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73039601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9987000226974487,"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":0.998199999332428,"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/bigram","display_name":"Bigram","score":0.9089827537536621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8295162916183472},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7595617175102234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6109346151351929},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5832928419113159},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5749201774597168},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5657005906105042},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5199195742607117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5073463320732117},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4925285279750824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41344547271728516},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08758172392845154},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08677420020103455}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9089827537536621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295162916183472},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7595617175102234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6109346151351929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5832928419113159},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5749201774597168},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5657005906105042},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5199195742607117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5073463320732117},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4925285279750824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41344547271728516},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08758172392845154},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08677420020103455},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/icassp49357.2023.10096812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1593247906","https://openalex.org/W2084534958","https://openalex.org/W2121879602","https://openalex.org/W2538246917","https://openalex.org/W2766219058","https://openalex.org/W2899879954","https://openalex.org/W2914120296","https://openalex.org/W2936774411","https://openalex.org/W2937197076","https://openalex.org/W2938348542","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2972437137","https://openalex.org/W3030437843","https://openalex.org/W3092189037","https://openalex.org/W3094841848","https://openalex.org/W3095732712","https://openalex.org/W3097777922","https://openalex.org/W3155453618","https://openalex.org/W3156323585","https://openalex.org/W3170360470","https://openalex.org/W4210463634","https://openalex.org/W6767737316","https://openalex.org/W6771467084","https://openalex.org/W6783990525"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W1700330385","https://openalex.org/W2002221802","https://openalex.org/W2041167939","https://openalex.org/W2250909759","https://openalex.org/W2562995433","https://openalex.org/W2131111393","https://openalex.org/W2028371633","https://openalex.org/W2020757772","https://openalex.org/W1500873938"],"abstract_inverted_index":{"Multilingual":[0],"automatic":[1],"speech":[2,59],"recognition":[3,36],"(ASR)":[4],"models":[5],"with":[6],"phones":[7],"as":[8,53,147],"modeling":[9,54],"units":[10,55],"have":[11,12,29],"improved":[13],"greatly":[14],"in":[15,86,104,119,133,156],"low-resource":[16,84,107,166],"and":[17,106,123,144],"similar-language":[18],"scenarios,":[19],"which":[20],"benefits":[21],"from":[22],"shared":[23],"representation":[24,128,149],"across":[25],"languages.":[26],"Meanwhile,":[27],"subwords":[28],"demonstrated":[30],"their":[31],"effectiveness":[32],"for":[33,56,69,82],"monolingual":[34],"end-to-end":[35,58],"systems.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,72,99,110],"investigate":[42],"the":[43,63,97,116,120,126,152],"use":[44,74],"of":[45,65,77],"phone-based":[46,66],"sub-words,":[47],"specifically":[48],"Byte":[49],"Pair":[50],"Encoding":[51],"(BPE),":[52],"multilingual":[57,70,78,134,157],"recognition.":[60],"To":[61],"explore":[62],"possibilities":[64],"BPE":[67,79,121,146,172],"(PBPE)":[68],"ASR,":[71],"first":[73],"three":[75,92],"types":[76],"training":[80],"methods":[81],"similar":[83,105],"languages":[85,95],"Central":[87],"Asia.":[88],"Then,":[89],"by":[90],"adding":[91],"high-resource":[93],"European":[94],"to":[96,114,130,169],"experiments,":[98],"analyze":[100],"language":[101,167],"sharing":[102],"degree":[103],"scenarios.":[108,135],"Finally,":[109],"propose":[111],"a":[112,160,165,170],"method":[113],"adjust":[115],"bigram":[117],"statistics":[118],"algorithm":[122],"show":[124,138],"that":[125,139],"PBPE":[127,140,154],"leads":[129],"accuracy":[131],"improvements":[132],"The":[136],"experiments":[137,158],"outperforms":[141],"phone,":[142],"character":[143],"character-based":[145,171],"output":[148],"units.":[150],"Particularly,":[151],"best":[153],"model":[155],"achieves":[159],"25%":[161],"relative":[162],"improvement":[163],"on":[164],"compared":[168],"system.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}