{"id":"https://openalex.org/W3196843354","doi":"https://doi.org/10.21437/interspeech.2021-958","title":"Data Augmentation Methods for End-to-End Speech Recognition on Distant-Talk Scenarios","display_name":"Data Augmentation Methods for End-to-End Speech Recognition on Distant-Talk Scenarios","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196843354","doi":"https://doi.org/10.21437/interspeech.2021-958","mag":"3196843354"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-958","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-958","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/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085150511","display_name":"Kentaro Shibata","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kentaro Shibata","raw_affiliation_strings":["Sony Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015372147","display_name":"Chaitanya Narisetty","orcid":"https://orcid.org/0000-0002-9239-5534"},"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":false,"raw_author_name":"Chaitanya Narisetty","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011937407"],"corresponding_institution_ids":["https://openalex.org/I2800278093"],"apc_list":null,"apc_paid":null,"fwci":1.3188,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83879732,"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":"301","last_page":"305"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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":0.8180713653564453},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7411412000656128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7399393320083618},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.680884599685669},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5985193848609924},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5800168514251709},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4602780044078827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4449908137321472},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3388546109199524},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10902315378189087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8180713653564453},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7411412000656128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7399393320083618},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.680884599685669},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5985193848609924},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5800168514251709},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4602780044078827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4449908137321472},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3388546109199524},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10902315378189087},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-958","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-958","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":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2099621636","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2559260703","https://openalex.org/W2726515241","https://openalex.org/W2766219058","https://openalex.org/W2794490148","https://openalex.org/W2808631503","https://openalex.org/W2883586237","https://openalex.org/W2890964092","https://openalex.org/W2899867592","https://openalex.org/W2900212944","https://openalex.org/W2902070858","https://openalex.org/W2903739847","https://openalex.org/W2936028438","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963057973","https://openalex.org/W2963581463","https://openalex.org/W2963736842","https://openalex.org/W2972818416","https://openalex.org/W2983061588","https://openalex.org/W3015280134","https://openalex.org/W3016400019","https://openalex.org/W3018441253","https://openalex.org/W3097777922","https://openalex.org/W3129625251","https://openalex.org/W3132613748","https://openalex.org/W3132806173","https://openalex.org/W3162649911","https://openalex.org/W3163793923","https://openalex.org/W4402490925"],"related_works":["https://openalex.org/W1972594981","https://openalex.org/W2136542423","https://openalex.org/W2045966063","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4398173524"],"abstract_inverted_index":{"Although":[0],"end-to-end":[1],"automatic":[2],"speech":[3,102],"recognition":[4],"(E2E":[5],"ASR)":[6],"has":[7],"achieved":[8,154],"great":[9],"performance":[10],"in":[11,42],"tasks":[12,59],"that":[13,132,166],"have":[14],"numerous":[15],"paired":[16],"data,":[17,83],"it":[18],"is":[19],"still":[20],"challenging":[21],"to":[22,69,92,107],"make":[23],"E2E":[24,40],"ASR":[25,41,45,120],"robust":[26],"against":[27,63],"noisy":[28,64,105],"and":[29,65,74,103,112],"low-resource":[30],"conditions.In":[31],"this":[32],"study,":[33],"we":[34,171],"investigated":[35],"data":[36,78],"augmentation":[37,72,79,90,115,134],"methods":[38,73],"for":[39,60,122,176],"distanttalk":[43],"scenarios.E2E":[44],"models":[46],"are":[47,57,148],"trained":[48,91],"on":[49,140],"the":[50,98,109,118,128,138,143,168,177],"series":[51],"of":[52,100,104,142,167],"CHiME":[53],"challenge":[54],"datasets,":[55],"which":[56,161],"suitable":[58],"studying":[61],"robustness":[62],"spontaneous":[66],"speech.We":[67],"propose":[68],"use":[70],"three":[71,174],"thier":[75],"combinations:":[76],"1)":[77],"using":[80,127],"text-to-speech":[81],"(TTS)":[82],"2)":[84],"cycleconsistent":[85],"generative":[86],"adversarial":[87],"network":[88],"(Cycle-GAN)":[89],"map":[93],"two":[94],"different":[95],"audio":[96],"characteristics,":[97],"one":[99],"clean":[101],"recordings,":[106],"match":[108],"testing":[110],"condition,":[111],"3)":[113],"pseudo-label":[114],"provided":[116],"by":[117,150],"pretrained":[119],"module":[121],"smoothing":[123],"label":[124],"distributions.Experimental":[125],"results":[126],"CHiME-6/CHiME-4":[129],"datasets":[130],"show":[131],"each":[133],"method":[135],"individually":[136],"improves":[137],"accuracy":[139],"top":[141],"conventional":[144],"SpecAugment;":[145],"further":[146],"improvements":[147],"obtained":[149],"combining":[151],"these":[152],"approaches.We":[153],"4.3%":[155],"word":[156],"error":[157],"rate":[158],"(WER)":[159],"reduction,":[160],"was":[162],"more":[163],"significant":[164],"than":[165],"SpecAugment,":[169],"when":[170],"combine":[172],"all":[173],"augmentations":[175],"CHiME-6":[178],"task.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}