{"id":"https://openalex.org/W2564008415","doi":"https://doi.org/10.1109/slt.2016.7846240","title":"Automatic optimization of data perturbation distributions for multi-style training in speech recognition","display_name":"Automatic optimization of data perturbation distributions for multi-style training in speech recognition","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2564008415","doi":"https://doi.org/10.1109/slt.2016.7846240","mag":"2564008415"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5037893785","display_name":"Mortaza Doulaty","orcid":"https://orcid.org/0000-0002-1773-7557"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mortaza Doulaty","raw_affiliation_strings":["University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077077136","display_name":"Richard C. Rose","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Rose","raw_affiliation_strings":["Google Inc., New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Google Inc., New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"27"},"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":0.9998000264167786,"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":0.9984999895095825,"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":0.765815258026123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7315242886543274},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5800196528434753},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5513248443603516},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.48456016182899475},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46738138794898987},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4583877623081207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3786657452583313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765815258026123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7315242886543274},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5800196528434753},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5513248443603516},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.48456016182899475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46738138794898987},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4583877623081207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3786657452583313},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2016.7846240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W2039285212","https://openalex.org/W2117678320","https://openalex.org/W2136439176","https://openalex.org/W2168510624","https://openalex.org/W2184343439","https://openalex.org/W2296748324","https://openalex.org/W2402865896","https://openalex.org/W2407080277","https://openalex.org/W2407204023","https://openalex.org/W6686369942","https://openalex.org/W6713419125","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2032415964","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W2340348677","https://openalex.org/W2130799169"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"performance":[2,187],"using":[3],"deep":[4],"neural":[5],"network":[6],"based":[7],"acoustic":[8,16,135,198],"models":[9],"is":[10,95,153,176],"known":[11],"to":[12,48,61,120,160,178],"degrade":[13],"when":[14,188],"the":[15,19,23,30,34,70,74,89,155,162,165,180,189],"environment":[17],"and":[18,55,141,147,168],"speaker":[20,142],"population":[21],"in":[22,33,51,122,164],"target":[24,64,90,106,166,190],"utterances":[25,50,103,121,191],"are":[26,128,192],"significantly":[27],"different":[28],"from":[29,104,194],"conditions":[31],"represented":[32],"training":[35,43,58,125,158],"data.":[36],"To":[37],"address":[38],"these":[39],"mismatched":[40,57],"scenarios,":[41],"multi-style":[42],"(MTR)":[44],"has":[45],"been":[46],"used":[47],"perturb":[49],"an":[52,110,123],"existing":[53,124],"uncorrupted":[54],"potentially":[56],"speech":[59,91],"corpus":[60],"better":[62],"match":[63],"domain":[65,167],"utterances.":[66,92],"This":[67],"paper":[68],"addresses":[69],"problem":[71],"of":[72,76,83,102,113,182],"determining":[73],"distribution":[75,112],"perturbation":[77,84,114,131],"levels":[78,115],"for":[79,130,154],"a":[80,99,105,195],"given":[81,98],"set":[82,101,159],"types":[85,132],"that":[86,116,133],"best":[87],"matches":[88],"An":[93,173],"approach":[94,184],"presented":[96],"that,":[97],"small":[100],"domain,":[107],"automatically":[108],"identifies":[109],"empirical":[111],"can":[117],"be":[118],"applied":[119],"set.":[126],"Distributions":[127],"estimated":[129],"include":[134],"background":[136],"environments,":[137],"reverberant":[138],"room":[139],"configurations,":[140],"related":[143],"variation":[144],"like":[145],"frequency":[146],"temporal":[148],"warping.":[149],"The":[150],"end":[151],"goal":[152],"resulting":[156],"perturbed":[157],"characterize":[161],"variability":[163],"thereby":[169],"optimize":[170],"ASR":[171,186],"performance.":[172],"experimental":[174],"study":[175],"performed":[177],"evaluate":[179],"impact":[181],"this":[183],"on":[185],"taken":[193],"simulated":[196],"far-field":[197],"environment.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}