{"id":"https://openalex.org/W3197976714","doi":"https://doi.org/10.21437/interspeech.2021-1162","title":"Semantic Data Augmentation for End-to-End Mandarin Speech Recognition","display_name":"Semantic Data Augmentation for End-to-End Mandarin Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197976714","doi":"https://doi.org/10.21437/interspeech.2021-1162","mag":"3197976714"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1162","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069057216","display_name":"Jianwei Sun","orcid":"https://orcid.org/0000-0002-2361-6823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianwei Sun","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039262837","display_name":"Hengxin Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengxin Yin","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392097","display_name":"Wei Wang","orcid":"https://orcid.org/0009-0000-5702-3009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700309","display_name":"Xi Zhao","orcid":"https://orcid.org/0000-0001-9108-5094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Zhao","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041886705","display_name":"Shuaijiang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuaijiang Zhao","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059708315","display_name":"Xiaoning Lei","orcid":"https://orcid.org/0009-0002-0518-7903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoning Lei","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808317","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4307-5355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["KE Holdings Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KE Holdings Inc, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1269","last_page":"1273"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8202632665634155},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.740246057510376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6437779664993286},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6170196533203125},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.552032470703125},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5164958834648132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4899417757987976},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.46729758381843567},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4467756748199463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43997856974601746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0806272029876709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202632665634155},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.740246057510376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6437779664993286},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6170196533203125},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.552032470703125},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5164958834648132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4899417757987976},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.46729758381843567},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4467756748199463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43997856974601746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0806272029876709},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1162","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W567804358","https://openalex.org/W854541894","https://openalex.org/W1560628829","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W2005708641","https://openalex.org/W2015412875","https://openalex.org/W2062164080","https://openalex.org/W2099621636","https://openalex.org/W2102113734","https://openalex.org/W2123442489","https://openalex.org/W2147768505","https://openalex.org/W2293596383","https://openalex.org/W2406366062","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2617258110","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2950367758","https://openalex.org/W2962826786","https://openalex.org/W2963418739","https://openalex.org/W2972818416","https://openalex.org/W2983434507","https://openalex.org/W3008480565","https://openalex.org/W3015449694","https://openalex.org/W3015654635","https://openalex.org/W3096615836","https://openalex.org/W3097777922"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2889144591","https://openalex.org/W4396816926","https://openalex.org/W2593532750","https://openalex.org/W2110442089","https://openalex.org/W2642467014","https://openalex.org/W2889523925"],"abstract_inverted_index":{"End-to-end":[0],"models":[1],"have":[2],"gradually":[3],"become":[4],"the":[5,14,28,43,55,66,71,75,78,83,86,91,98,126,135,144],"preferred":[6],"option":[7],"for":[8,26,48,116,156],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"applications.During":[13],"training":[15,117],"of":[16,42,70,108,151],"end-to-end":[17,49],"ASR,":[18],"data":[19,35,110,157],"augmentation":[20,36],"is":[21,114],"a":[22,33,103,118],"quite":[23],"effective":[24],"technique":[25,37],"regularizing":[27],"neural":[29],"networks.This":[30],"paper":[31],"proposes":[32],"novel":[34],"based":[38,57,96,130],"on":[39,58,82,97,125],"semantic":[40],"transposition":[41,61],"transcriptions":[44,56],"via":[45],"syntax":[46],"rules":[47],"Mandarin":[50],"ASR.Specifically,":[51],"we":[52],"first":[53],"segment":[54],"part-of-speech":[59],"tags.Then":[60],"strategies,":[62],"such":[63,148],"as":[64,149],"placing":[65],"object":[67],"in":[68],"front":[69],"subject":[72,76],"or":[73],"swapping":[74],"and":[77,111,128,154],"object,":[79],"are":[80,94,123,159],"applied":[81],"segmented":[84],"sentences.Finally,":[85],"acoustic":[87],"features":[88],"corresponding":[89],"to":[90,143],"transposed":[92],"transcription":[93],"reassembled":[95],"audio-to-text":[99],"forced-alignment":[100],"produced":[101],"by":[102],"pre-trained":[104],"ASR":[105,120],"system.The":[106,121],"combination":[107,158],"original":[109],"augmented":[112],"one":[113],"used":[115],"new":[119],"experiments":[122],"conducted":[124],"Transformer[1]":[127],"Conformer[2]":[129],"ASR.The":[131],"results":[132],"show":[133],"that":[134],"proposed":[136],"method":[137],"can":[138],"give":[139],"consistent":[140],"performance":[141],"gain":[142],"system.Augmentation":[145],"related":[146],"issues,":[147],"comparison":[150],"different":[152],"strategies":[153],"ratios":[155],"also":[160],"investigated.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}