{"id":"https://openalex.org/W4372259817","doi":"https://doi.org/10.1109/icassp49357.2023.10095326","title":"Improving Massively Multilingual ASR with Auxiliary CTC Objectives","display_name":"Improving Massively Multilingual ASR with Auxiliary CTC Objectives","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259817","doi":"https://doi.org/10.1109/icassp49357.2023.10095326"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095326","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":"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/A5101779022","display_name":"William Chen","orcid":"https://orcid.org/0000-0002-3251-3084"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Chen","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA","Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA","Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA","Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA","Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA","Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA","Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101779022"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.5186,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9564659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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":0.8958873748779297},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.782968282699585},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5929320454597473},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5243911147117615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512906551361084},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4954138994216919},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4813885986804962},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4598046839237213},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.424822062253952},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3909469246864319},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3042334318161011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8958873748779297},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.782968282699585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5929320454597473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5243911147117615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512906551361084},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4954138994216919},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4813885986804962},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4598046839237213},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.424822062253952},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3909469246864319},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3042334318161011},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095326","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":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W2058094241","https://openalex.org/W2127141656","https://openalex.org/W2292087804","https://openalex.org/W2407080277","https://openalex.org/W2766219058","https://openalex.org/W2786835190","https://openalex.org/W2884975363","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963431393","https://openalex.org/W3015877095","https://openalex.org/W3015960524","https://openalex.org/W3030437843","https://openalex.org/W3095410713","https://openalex.org/W3096032230","https://openalex.org/W3096215352","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3162249256","https://openalex.org/W3163793923","https://openalex.org/W3178647810","https://openalex.org/W3196485121","https://openalex.org/W3197140813","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3205920203","https://openalex.org/W3206573929","https://openalex.org/W3209984917","https://openalex.org/W3212799896","https://openalex.org/W3213029956","https://openalex.org/W3217003515","https://openalex.org/W4210463634","https://openalex.org/W4221152838","https://openalex.org/W4221155340","https://openalex.org/W4225295099","https://openalex.org/W4226033575","https://openalex.org/W4285070048","https://openalex.org/W4296068421","https://openalex.org/W4296069143","https://openalex.org/W4297841565","https://openalex.org/W4300939116","https://openalex.org/W4311000453","https://openalex.org/W4319862218","https://openalex.org/W4319862635","https://openalex.org/W4372269205","https://openalex.org/W4385245566","https://openalex.org/W4386566728","https://openalex.org/W6696449567","https://openalex.org/W6739901393","https://openalex.org/W6771467084","https://openalex.org/W6774503009","https://openalex.org/W6779919476","https://openalex.org/W6804030475","https://openalex.org/W6810259195","https://openalex.org/W6838599634","https://openalex.org/W6838929754","https://openalex.org/W6840202044","https://openalex.org/W6846002384","https://openalex.org/W6846865774","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W2504816413"],"abstract_inverted_index":{"Multilingual":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"models":[5,24,127,147],"have":[6,25],"extended":[7],"the":[8,43,71,91,94,101,111,129,134],"usability":[9],"of":[10,17,97,104,113,136],"speech":[11],"technologies":[12],"to":[13,26,31,40,89],"a":[14,29,64,142],"wide":[15],"variety":[16],"languages.":[18],"With":[19],"how":[20],"many":[21],"languages":[22,38],"these":[23],"handle,":[27],"however,":[28],"key":[30],"understanding":[32],"their":[33],"imbalanced":[34],"performance":[35,61],"across":[36],"different":[37],"is":[39],"examine":[41],"if":[42],"model":[44,73,92],"actually":[45],"knows":[46],"which":[47],"language":[48,75],"it":[49],"should":[50],"transcribe.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"introduce":[56],"our":[57,114,122],"work":[58,138],"on":[59,62,74,100,139],"improving":[60],"FLEURS,":[63],"102-language":[65],"open":[66],"ASR":[67],"benchmark,":[68],"by":[69,141],"conditioning":[70,99],"entire":[72],"identity":[76],"(LID).":[77],"We":[78],"investigate":[79],"techniques":[80],"inspired":[81],"from":[82],"recent":[83],"Connectionist":[84],"Temporal":[85],"Classification":[86],"(CTC)":[87],"studies":[88],"help":[90],"handle":[93],"large":[95],"number":[96],"languages,":[98],"LID":[102],"predictions":[103],"auxiliary":[105],"tasks.":[106],"Our":[107],"experimental":[108],"results":[109,135],"demonstrate":[110],"effectiveness":[112],"technique":[115],"over":[116,133],"standard":[117],"CTC/Attention-based":[118],"hybrid":[119],"models.":[120],"Furthermore,":[121],"state-of-the-art":[123],"systems":[124],"using":[125],"self-supervised":[126],"with":[128],"Conformer":[130],"architecture":[131],"improve":[132],"prior":[137],"FLEURS":[140],"relative":[143],"28.4%":[144],"CER.":[145],"Trained":[146],"are":[148,151],"reproducible":[149],"recipes":[150],"available":[152],"at":[153],"https://github.com/espnet/espnet/tree/master/egs2/fleurs/asr1.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}