{"id":"https://openalex.org/W2926989360","doi":"https://doi.org/10.21437/interspeech.2019-1867","title":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","display_name":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2926989360","doi":"https://doi.org/10.21437/interspeech.2019-1867","mag":"2926989360"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1867","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":["Nanyang Technological Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological Univ","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["Nanyang Technological Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological Univ","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046222772","display_name":"Van Tung Pham","orcid":"https://orcid.org/0000-0002-2103-1901"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Tung Pham","raw_affiliation_strings":["Nanyang Technological Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological Univ","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107992032","display_name":"Zhiping Zeng","orcid":"https://orcid.org/0000-0003-1165-8812"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiping Zeng","raw_affiliation_strings":["Nanyang Technological Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological Univ","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological Univ","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["alibaba group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"alibaba group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["alibaba group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"alibaba group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.756,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89003997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2160","last_page":"2164"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","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/code-switching","display_name":"Code-switching","score":0.8629498481750488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929085493087769},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6190440654754639},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.594285249710083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5779541730880737},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5566203594207764},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5517638325691223},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5113705992698669},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.4258078336715698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3263353705406189},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3058036267757416},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2500147819519043},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07085466384887695}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.8629498481750488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929085493087769},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6190440654754639},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.594285249710083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5779541730880737},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5566203594207764},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5517638325691223},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5113705992698669},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.4258078336715698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3263353705406189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3058036267757416},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2500147819519043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07085466384887695},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1867","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03802","pdf_url":"https://arxiv.org/pdf/1904.03802","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03802","pdf_url":"https://arxiv.org/pdf/1904.03802","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W2127141656","https://openalex.org/W2134817403","https://openalex.org/W2407080277","https://openalex.org/W2627092829","https://openalex.org/W2798348125","https://openalex.org/W2883989418","https://openalex.org/W2889213362","https://openalex.org/W2896068220","https://openalex.org/W2896558859","https://openalex.org/W2899073901","https://openalex.org/W2900139003","https://openalex.org/W2913851961","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2962835968","https://openalex.org/W2963362078","https://openalex.org/W2964156075","https://openalex.org/W2972417954","https://openalex.org/W2972702443"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W4389976243","https://openalex.org/W2432897346","https://openalex.org/W2381926679","https://openalex.org/W2181336723","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2974240475"],"abstract_inverted_index":{"The":[0,79],"lack":[1],"of":[2,8,15,46,50,85,99,113],"code-switch":[3,64],"training":[4],"data":[5],"is":[6],"one":[7],"the":[9,13,44,59,93,97,114],"major":[10],"concerns":[11],"in":[12],"development":[14],"end-to-end":[16,34],"code-switching":[17,35,128],"automatic":[18],"speech":[19],"recognition":[20],"(ASR)":[21],"models.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,68],"propose":[27,69],"a":[28],"method":[29,42],"to":[30,53,62,70,88,102,105,119],"train":[31],"an":[32],"improved":[33],"ASR":[36,60,129],"using":[37],"only":[38],"monolingual":[39,51,86],"data.":[40],"Our":[41],"encourages":[43],"distributions":[45,101],"output":[47,83],"token":[48],"embeddings":[49,84],"languages":[52,87],"be":[54,103],"similar,":[55],"and":[56,74],"hence,":[57],"promotes":[58],"model":[61],"easily":[63],"between":[65],"languages.":[66],"Specifically,":[67],"use":[71],"Jensen-Shannon":[72],"divergence":[73],"cosine":[75],"distance":[76],"based":[77],"constraints.":[78],"former":[80],"will":[81],"enforce":[82],"possess":[89],"similar":[90],"distributions,":[91],"while":[92],"later":[94],"simply":[95],"brings":[96],"centroids":[98],"two":[100],"close":[104],"each":[106],"other.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"high":[111],"effectiveness":[112],"proposed":[115],"method,":[116],"yielding":[117],"up":[118],"4.5%":[120],"absolute":[121],"mixed":[122],"error":[123],"rate":[124],"improvement":[125],"on":[126],"Mandarin-English":[127],"task.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2019-04-11T00:00:00"}
