{"id":"https://openalex.org/W3096615836","doi":"https://doi.org/10.1109/slt48900.2021.9383620","title":"Data Augmentation for end-to-end Code-Switching Speech Recognition","display_name":"Data Augmentation for end-to-end Code-Switching Speech Recognition","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3096615836","doi":"https://doi.org/10.1109/slt48900.2021.9383620","mag":"3096615836"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/2011.02160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348721","display_name":"Hao Li","orcid":"https://orcid.org/0009-0005-4319-9026"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070663","display_name":"Yizhou Lu","orcid":"https://orcid.org/0000-0003-1399-8079"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Lu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363636","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0001-7925-7957"},"institutions":[{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology","institution_ids":["https://openalex.org/I4210115303","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"200"},"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":0.9998000264167786,"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":0.9983000159263611,"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/code-switching","display_name":"Code-switching","score":0.9128811955451965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7980456948280334},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6749784350395203},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5466766953468323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.54317307472229},{"id":"https://openalex.org/keywords/code-word","display_name":"Code word","score":0.4662555456161499},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45866265892982483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3375903069972992},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.32106927037239075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16497889161109924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15771585702896118}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.9128811955451965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980456948280334},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6749784350395203},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5466766953468323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.54317307472229},{"id":"https://openalex.org/C153207627","wikidata":"https://www.wikidata.org/wiki/Q863873","display_name":"Code word","level":3,"score":0.4662555456161499},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45866265892982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375903069972992},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.32106927037239075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16497889161109924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15771585702896118},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt48900.2021.9383620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02160","pdf_url":"https://arxiv.org/pdf/2011.02160","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:2011.02160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02160","pdf_url":"https://arxiv.org/pdf/2011.02160","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1959608418","https://openalex.org/W2059588204","https://openalex.org/W2062164080","https://openalex.org/W2099621636","https://openalex.org/W2102113734","https://openalex.org/W2114569717","https://openalex.org/W2120847449","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2584505851","https://openalex.org/W2766219058","https://openalex.org/W2794490148","https://openalex.org/W2795935804","https://openalex.org/W2891616026","https://openalex.org/W2892009249","https://openalex.org/W2896558859","https://openalex.org/W2899299209","https://openalex.org/W2901607128","https://openalex.org/W2926989360","https://openalex.org/W2936774411","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963272440","https://openalex.org/W2963403868","https://openalex.org/W2964156075","https://openalex.org/W2970730223","https://openalex.org/W2972417954","https://openalex.org/W2972818416","https://openalex.org/W2991090520","https://openalex.org/W3007328579","https://openalex.org/W3007948236","https://openalex.org/W3015654635","https://openalex.org/W3030986950","https://openalex.org/W3134568285","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6640963894","https://openalex.org/W6675365184","https://openalex.org/W6675409298","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755574360","https://openalex.org/W6756627502","https://openalex.org/W6763832098","https://openalex.org/W6771006410","https://openalex.org/W6774435279"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W4389976243","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2090054304","https://openalex.org/W98604564"],"abstract_inverted_index":{"Training":[0],"a":[1,11],"code-switching":[2,17,31,42,48,63,76],"end-to-end":[3],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"model":[8],"normally":[9],"requires":[10],"large":[12],"amount":[13],"of":[14],"data,":[15,43],"while":[16],"data":[18,32,111],"is":[19,99],"often":[20],"limited.":[21],"In":[22],"this":[23],"paper,":[24],"three":[25,69],"novel":[26],"approaches":[27,71,83],"are":[28,36],"proposed":[29,70,82],"for":[30],"augmentation.":[33],"Specifically,":[34],"they":[35],"audio":[37],"splicing":[38],"with":[39,46,87,122],"the":[40,68,81,107,120],"existing":[41],"and":[44,91,113],"TTS":[45],"new":[47],"texts":[49],"generated":[50],"by":[51,102],"word":[52,55],"translation":[53],"or":[54],"insertion.":[56],"Our":[57],"experiments":[58],"on":[59,75],"200":[60],"hours":[61],"Mandarin-English":[62],"dataset":[64],"show":[65],"that":[66],"all":[67,80],"yield":[72],"significant":[73],"improvements":[74],"ASR":[77],"individually.":[78],"Moreover,":[79],"can":[84,95],"be":[85,96],"combined":[86],"recent":[88],"popular":[89],"SpecAugment,":[90],"an":[92],"addition":[93],"gain":[94,117],"obtained.":[97],"WER":[98],"significantly":[100],"reduced":[101],"relative":[103,115],"24.0%":[104],"compared":[105,118],"to":[106,119],"system":[108,121],"without":[109],"any":[110],"augmentation,":[112],"still":[114],"13.0%":[116],"only":[123],"SpecAugment.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}