{"id":"https://openalex.org/W3094197178","doi":"https://doi.org/10.1109/icassp39728.2021.9414478","title":"How Phonotactics Affect Multilingual and Zero-Shot ASR Performance","display_name":"How Phonotactics Affect Multilingual and Zero-Shot ASR Performance","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3094197178","doi":"https://doi.org/10.1109/icassp39728.2021.9414478","mag":"3094197178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.12104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Zelasko","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laureano Moro-Velazquez","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062172410","display_name":"Ali Abavisani","orcid":"https://orcid.org/0000-0003-4235-9022"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Abavisani","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4982,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84852732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7238","last_page":"7242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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/phonotactics","display_name":"Phonotactics","score":0.9024008512496948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8310874700546265},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6192370057106018},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5517234802246094},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5313135981559753},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5214444994926453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165044665336609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5113579630851746},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4234650135040283},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19704461097717285},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.11094722151756287}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.9024008512496948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310874700546265},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6192370057106018},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5517234802246094},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5313135981559753},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5214444994926453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165044665336609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5113579630851746},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4234650135040283},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19704461097717285},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.11094722151756287},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.12104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12104","pdf_url":"https://arxiv.org/pdf/2010.12104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:tudelft.nl:uuid:c035edc6-688f-4d16-aa77-45351266dba2","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:c035edc6-688f-4d16-aa77-45351266dba2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.12104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12104","pdf_url":"https://arxiv.org/pdf/2010.12104","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"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/W66627554","https://openalex.org/W86969866","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W2025198378","https://openalex.org/W2085628288","https://openalex.org/W2120209245","https://openalex.org/W2147768505","https://openalex.org/W2158069733","https://openalex.org/W2316803017","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2888867175","https://openalex.org/W3005578234","https://openalex.org/W3015877095","https://openalex.org/W3016010032","https://openalex.org/W3025286576","https://openalex.org/W3045485643","https://openalex.org/W3088761213","https://openalex.org/W3095732712","https://openalex.org/W3095838132","https://openalex.org/W6602682705","https://openalex.org/W6631362777","https://openalex.org/W6713762819","https://openalex.org/W6774503009"],"related_works":["https://openalex.org/W2615317726","https://openalex.org/W2021909761","https://openalex.org/W198649858","https://openalex.org/W2467354670","https://openalex.org/W2498910126","https://openalex.org/W2497306275","https://openalex.org/W1602082497","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"The":[0],"idea":[1],"of":[2,19,22,42,68,116,128,141],"combining":[3],"multiple":[4],"languages\u2019":[5],"recordings":[6],"to":[7,34,58,80],"train":[8],"a":[9,27,111,117,139,159,172,176],"single":[10],"automatic":[11],"speech":[12,24],"recognition":[13],"(ASR)":[14],"model":[15,30,63,71,75,162],"brings":[16],"the":[17,20,48,69,83,91,100,108,149,165,184],"promise":[18],"emergence":[21],"universal":[23],"representation.":[25],"Recently,":[26],"Transformer":[28],"encoder-decoder":[29,109],"has":[31],"been":[32],"shown":[33],"leverage":[35],"multilingual":[36,173,177],"data":[37,188],"well":[38],"in":[39,55,88,93,189],"IPA":[40],"transcriptions":[41],"languages":[43],"presented":[44],"during":[45],"training.":[46],"However,":[47],"representations":[49],"it":[50,77],"learned":[51],"were":[52],"not":[53],"successful":[54],"zero-shot":[56,103,166],"transfer":[57],"unseen":[59],"languages.":[60,145],"Because":[61],"that":[62,148,171],"lacks":[64],"an":[65,125],"explicit":[66],"factorization":[67],"acoustic":[70,134],"(AM)":[72],"and":[73,120,131,135,157,181],"language":[74,136],"(LM),":[76],"is":[78,155,192],"unclear":[79],"what":[81],"degree":[82],"performance":[84],"suffered":[85],"from":[86,151],"differences":[87],"pronunciation":[89],"or":[90],"mismatch":[92],"phono-tactics.":[94],"To":[95],"gain":[96,150],"more":[97],"insight":[98],"into":[99],"factors":[101],"limiting":[102],"ASR":[104,113,178],"transfer,":[105],"we":[106,123,169],"replace":[107],"with":[110],"hybrid":[112],"system":[114],"consisting":[115],"separate":[118],"AM":[119],"LM.":[121],"Then,":[122],"perform":[124],"extensive":[126],"evaluation":[127],"monolingual,":[129],"multilingual,":[130],"crosslingual":[132,153],"(zero-shot)":[133],"models":[137],"on":[138],"set":[140],"13":[142],"phonetically":[143],"diverse":[144],"We":[146],"show":[147],"modeling":[152],"phonotactics":[154],"limited,":[156],"imposing":[158],"too":[160],"strong":[161],"can":[163],"hurt":[164],"transfer.":[167],"Furthermore,":[168],"find":[170],"LM":[174,190],"hurts":[175],"system\u2019s":[179],"performance,":[180],"retaining":[182],"only":[183],"target":[185],"language\u2019s":[186],"phonotactic":[187],"training":[191],"preferable.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
