{"id":"https://openalex.org/W3015877095","doi":"https://doi.org/10.1109/icassp40776.2020.9054362","title":"Universal Phone Recognition with a Multilingual Allophone System","display_name":"Universal Phone Recognition with a Multilingual Allophone System","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015877095","doi":"https://doi.org/10.1109/icassp40776.2020.9054362","mag":"3015877095"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"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":"Xinjian Li","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"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":"Siddharth Dalmia","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"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":"Juncheng Li","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103062339","display_name":"Matthew Lee","orcid":"https://orcid.org/0000-0002-7160-8625"},"institutions":[{"id":"https://openalex.org/I1322829787","display_name":"SIL International","ror":"https://ror.org/00d57b563","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1322829787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Lee","raw_affiliation_strings":["SIL International"],"affiliations":[{"raw_affiliation_string":"SIL International","institution_ids":["https://openalex.org/I1322829787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045031910","display_name":"Patrick Littell","orcid":"https://orcid.org/0000-0002-7173-0225"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Littell","raw_affiliation_strings":["National Research Council Canada"],"affiliations":[{"raw_affiliation_string":"National Research Council Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102857591","display_name":"Jiali Yao","orcid":"https://orcid.org/0009-0009-9673-3658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiali Yao","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"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":"Antonios Anastasopoulos","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"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":"David R. Mortensen","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"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":"Graham Neubig","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"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":"Alan W Black","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100660610"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":10.7461,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.98672041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8249","last_page":"8253"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.8546404838562012},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.8015550374984741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5581995248794556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5408085584640503},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5243402123451233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5033978819847107},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46585971117019653},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4270181953907013},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14813369512557983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546404838562012},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.8015550374984741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5581995248794556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5408085584640503},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5243402123451233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5033978819847107},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46585971117019653},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4270181953907013},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14813369512557983},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:f24db854-9c47-4182-8445-ec6e442c1652","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=f24db854-9c47-4182-8445-ec6e442c1652","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"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/W2195354","https://openalex.org/W73572011","https://openalex.org/W156922528","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1963727751","https://openalex.org/W2025198378","https://openalex.org/W2033436836","https://openalex.org/W2127141656","https://openalex.org/W2130414229","https://openalex.org/W2166637769","https://openalex.org/W2170101319","https://openalex.org/W2250357346","https://openalex.org/W2284628133","https://openalex.org/W2755682845","https://openalex.org/W2786835190","https://openalex.org/W2805993470","https://openalex.org/W2883972335","https://openalex.org/W2904840750","https://openalex.org/W2910959333","https://openalex.org/W2963242190","https://openalex.org/W2963292011","https://openalex.org/W2964227218","https://openalex.org/W2964309797","https://openalex.org/W2972581290","https://openalex.org/W2998284473","https://openalex.org/W3034729383","https://openalex.org/W6602987424","https://openalex.org/W6606306245","https://openalex.org/W6631362777","https://openalex.org/W6691509046","https://openalex.org/W6752124048","https://openalex.org/W6753999702","https://openalex.org/W6757499777","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2061937230","https://openalex.org/W2285081780","https://openalex.org/W2080458333","https://openalex.org/W62743518","https://openalex.org/W2143620265","https://openalex.org/W2390120011","https://openalex.org/W2003136674","https://openalex.org/W2141994339","https://openalex.org/W2377867028","https://openalex.org/W2610894233"],"abstract_inverted_index":{"Multilingual":[0,16],"models":[1],"can":[2,28,51,67,125,145],"improve":[3],"language":[4,48,150],"processing,":[5],"particularly":[6],"for":[7,181],"low":[8],"resource":[9],"situations,":[10],"by":[11,107],"sharing":[12],"parameters":[13],"across":[14],"languages.":[15],"acoustic":[17],"models,":[18],"however,":[19],"generally":[20],"ignore":[21],"the":[22,135,185],"difference":[23],"between":[24],"phonemes":[25,66],"(sounds":[26],"that":[27,42,101,163],"support":[29],"lexical":[30],"contrasts":[31],"in":[32,113,184],"a":[33,58,81,127,175],"particular":[34],"language)":[35],"and":[36,88,160],"their":[37],"corresponding":[38],"phones":[39],"(the":[40],"sounds":[41],"are":[43,47,119],"actually":[44,68],"spoken,":[45],"which":[46],"independent).":[49],"This":[50],"lead":[52],"to":[53,70,178],"performance":[54,106],"degradation":[55],"when":[56,132],"combining":[57],"variety":[59],"of":[60,84,142,170],"training":[61],"languages,":[62,98,158],"as":[63],"identically":[64],"annotated":[65],"correspond":[69],"several":[71],"different":[72],"underlying":[73],"phonetic":[74],"realizations.":[75],"In":[76,92],"this":[77,102],"work,":[78],"we":[79,99,118,124],"propose":[80],"joint":[82],"model":[83,103],"both":[85],"language-independent":[86,122],"phone":[87,129,143,167],"language-dependent":[89],"phoneme":[90,109],"distributions.":[91],"multilingual":[93],"ASR":[94],"experiments":[95],"over":[96],"11":[97],"find":[100],"improves":[104],"testing":[105],"2%":[108],"error":[110],"rate":[111],"absolute":[112],"low-resource":[114],"conditions.":[115],"Additionally,":[116],"because":[117],"explicitly":[120],"modeling":[121],"phones,":[123],"build":[126],"(nearly-)universal":[128],"recognizer":[130,165],"that,":[131],"combined":[133],"with":[134],"PHOIBLE":[136],"[1]":[137],"large,":[138],"manually":[139],"curated":[140],"database":[141],"inventories,":[144],"be":[146],"customized":[147],"into":[148],"2,000":[149],"dependent":[151],"recognizers.":[152],"Experiments":[153],"on":[154],"two":[155],"low-resourced":[156],"indigenous":[157],"Inuktitut":[159],"Tusom,":[161],"show":[162],"our":[164],"achieves":[166],"accuracy":[168],"improvements":[169],"more":[171],"than":[172],"17%,":[173],"moving":[174],"step":[176],"closer":[177],"speech":[179],"recognition":[180],"all":[182],"languages":[183],"world.":[186],"<sup":[187],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[189]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":11}],"updated_date":"2026-03-02T08:37:19.008085","created_date":"2025-10-10T00:00:00"}