{"id":"https://openalex.org/W3109396817","doi":"https://doi.org/10.1109/icassp39728.2021.9413562","title":"Transformer-Transducers for Code-Switched Speech Recognition","display_name":"Transformer-Transducers for Code-Switched Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3109396817","doi":"https://doi.org/10.1109/icassp39728.2021.9413562","mag":"3109396817"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413562","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.15023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Carnegie Mellon University, USA","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000919546","display_name":"Yuzong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Yuzong Liu","raw_affiliation_strings":["Amazon AWS AI, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Srikanth Ronanki","raw_affiliation_strings":["Amazon AWS AI, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Amazon AWS AI, USA","Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068873086"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51523838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5859","last_page":"5863"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9979000091552734,"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":0.7772955894470215},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6944898366928101},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.6512277126312256},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6434903144836426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6005480289459229},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5929529666900635},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5900273323059082},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5888898372650146},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.43407073616981506},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.419197678565979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3829057514667511},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37851834297180176},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1505003273487091},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10908213257789612},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07615360617637634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772955894470215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6944898366928101},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.6512277126312256},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6434903144836426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6005480289459229},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5929529666900635},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5900273323059082},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5888898372650146},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.43407073616981506},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.419197678565979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3829057514667511},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37851834297180176},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1505003273487091},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10908213257789612},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07615360617637634},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413562","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:2011.15023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.15023","pdf_url":"https://arxiv.org/pdf/2011.15023","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":"","raw_type":"text"},{"id":"mag:3109396817","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.15023.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.15023","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.15023","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/mza1-c341","is_oa":true,"landing_page_url":"https://doi.org/10.17023/mza1-c341","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.15023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.15023","pdf_url":"https://arxiv.org/pdf/2011.15023","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3109396817.pdf","grobid_xml":"https://content.openalex.org/works/W3109396817.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1992912377","https://openalex.org/W2099808146","https://openalex.org/W2126243000","https://openalex.org/W2127141656","https://openalex.org/W2153433699","https://openalex.org/W2251321385","https://openalex.org/W2252095989","https://openalex.org/W2327501763","https://openalex.org/W2346660049","https://openalex.org/W2526425061","https://openalex.org/W2548378118","https://openalex.org/W2739427748","https://openalex.org/W2750499125","https://openalex.org/W2769437540","https://openalex.org/W2809978471","https://openalex.org/W2892009249","https://openalex.org/W2894835365","https://openalex.org/W2911876655","https://openalex.org/W2914699162","https://openalex.org/W2926989360","https://openalex.org/W2928484296","https://openalex.org/W2936774411","https://openalex.org/W2937754410","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963242190","https://openalex.org/W2963266340","https://openalex.org/W2963292011","https://openalex.org/W2963403868","https://openalex.org/W2963443335","https://openalex.org/W2963827914","https://openalex.org/W2963952470","https://openalex.org/W2972417954","https://openalex.org/W2972888990","https://openalex.org/W2982413405","https://openalex.org/W2989224798","https://openalex.org/W3007227084","https://openalex.org/W3007948236","https://openalex.org/W3015315932","https://openalex.org/W3016010032","https://openalex.org/W3028545098","https://openalex.org/W3096686110","https://openalex.org/W3097306574","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6688167117","https://openalex.org/W6691537765","https://openalex.org/W6691770337","https://openalex.org/W6734807902","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6746041127","https://openalex.org/W6760937267","https://openalex.org/W6769806307","https://openalex.org/W6770250107","https://openalex.org/W6774435279"],"related_works":["https://openalex.org/W3160201895","https://openalex.org/W2893964394","https://openalex.org/W3209162484","https://openalex.org/W2899073901","https://openalex.org/W3016108605","https://openalex.org/W3008092184","https://openalex.org/W2911876655","https://openalex.org/W2972417954","https://openalex.org/W3097306574","https://openalex.org/W2937754410","https://openalex.org/W3081905069","https://openalex.org/W2939757332","https://openalex.org/W3198544738","https://openalex.org/W3034335198","https://openalex.org/W3196389490","https://openalex.org/W2899299209","https://openalex.org/W3012101946","https://openalex.org/W2914699162","https://openalex.org/W3035687429","https://openalex.org/W3021744364"],"abstract_inverted_index":{"We":[0,78,145],"live":[1],"in":[2,86],"a":[3,27,43,70,111,132,157,163],"world":[4],"where":[5],"60%":[6],"of":[7,18,92,106,149,167],"the":[8,39,83,103,122,138,147,154],"population":[9],"can":[10,49],"speak":[11],"two":[12,97],"or":[13,57],"more":[14],"languages":[15,24,52],"fluently.":[16],"Members":[17],"these":[19],"communities":[20],"constantly":[21],"switch":[22],"between":[23],"when":[25],"having":[26],"conversation.":[28],"As":[29],"automatic":[30],"speech":[31,76,141],"recognition":[32],"(ASR)":[33],"systems":[34,47],"are":[35],"being":[36],"deployed":[37],"to":[38,88,101,120,136],"real-world,":[40],"there":[41],"is":[42],"need":[44],"for":[45,74],"practical":[46],"that":[48],"handle":[50,89,102],"multiple":[51],"both":[53],"within":[54],"an":[55,65],"utterance":[56],"across":[58],"utterances.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,95,109,130],"present":[64],"end-to-end":[66],"ASR":[67],"system":[68],"using":[69],"transformer-transducer":[71],"model":[72,85],"architecture":[73],"code-switched":[75],"recognition.":[77],"propose":[79,110,131],"three":[80],"modifications":[81],"over":[82],"vanilla":[84],"order":[87],"various":[90],"aspects":[91],"code-switching.":[93,107,128,144],"First,":[94],"introduce":[96],"auxiliary":[98],"loss":[99],"functions":[100],"low-resource":[104],"scenario":[105],"Second,":[108],"novel":[112],"mask-based":[113],"training":[114,125],"strategy":[115],"with":[116],"language":[117],"ID":[118],"information":[119],"improve":[121],"label":[123],"encoder":[124,134],"towards":[126,143],"intra-sentential":[127],"Finally,":[129],"multi-label/multi-audio":[133],"structure":[135],"leverage":[137],"vast":[139],"monolingual":[140],"corpora":[142],"demonstrate":[146],"efficacy":[148],"our":[150],"proposed":[151],"approaches":[152],"on":[153,171],"SEAME":[155],"dataset,":[156],"public":[158],"Mandarin-English":[159],"code-switching":[160],"corpus,":[161],"achieving":[162],"mixed":[164],"error":[165],"rate":[166],"18.5%":[168],"and":[169,176],"26.3%":[170],"test":[172,177],"<inf":[173,178],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174,179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">man</inf>":[175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sge</inf>":[180],"sets":[181],"respectively.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}