{"id":"https://openalex.org/W1979651826","doi":"https://doi.org/10.1109/taslp.2015.2438544","title":"Data Augmentation for Deep Neural Network Acoustic Modeling","display_name":"Data Augmentation for Deep Neural Network Acoustic Modeling","publication_year":2015,"publication_date":"2015-06-03","ids":{"openalex":"https://openalex.org/W1979651826","doi":"https://doi.org/10.1109/taslp.2015.2438544","mag":"1979651826"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2438544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2438544","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":30.5573,"has_fulltext":false,"cited_by_count":374,"citation_normalized_percentile":{"value":0.99683132,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"23","issue":"9","first_page":"1469","last_page":"1477"},"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.801362156867981},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6454305052757263},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6376287937164307},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6289058923721313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6259422302246094},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6027473211288452},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5790808200836182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5183364152908325},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47935277223587036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4654895067214966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801362156867981},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6454305052757263},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6376287937164307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6289058923721313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6259422302246094},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6027473211288452},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5790808200836182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183364152908325},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47935277223587036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4654895067214966},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2438544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2438544","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W84880661","https://openalex.org/W1509793305","https://openalex.org/W1654807615","https://openalex.org/W1967260196","https://openalex.org/W1974205368","https://openalex.org/W1984570643","https://openalex.org/W1989674786","https://openalex.org/W1995562189","https://openalex.org/W2002342963","https://openalex.org/W2013996527","https://openalex.org/W2028706510","https://openalex.org/W2039285212","https://openalex.org/W2048985487","https://openalex.org/W2056714990","https://openalex.org/W2080401855","https://openalex.org/W2099621636","https://openalex.org/W2103635001","https://openalex.org/W2106554350","https://openalex.org/W2112796928","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2136439176","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2155117693","https://openalex.org/W2156142001","https://openalex.org/W2156163116","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2164931619","https://openalex.org/W2170794967","https://openalex.org/W2184045248","https://openalex.org/W2184343439","https://openalex.org/W2187428966","https://openalex.org/W2292087804","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2407115099","https://openalex.org/W2442329935","https://openalex.org/W2962719052","https://openalex.org/W6602023532","https://openalex.org/W6603374476","https://openalex.org/W6636948317","https://openalex.org/W6653852971","https://openalex.org/W6675409298","https://openalex.org/W6684191040","https://openalex.org/W6686369942","https://openalex.org/W6686973839","https://openalex.org/W6696449567","https://openalex.org/W6713386538","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W4200173597","https://openalex.org/W2915754718","https://openalex.org/W4299822940","https://openalex.org/W2279398222","https://openalex.org/W3000866861","https://openalex.org/W2955560448"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"data":[3,18,21,61,71,82],"augmentation":[4,22,83],"for":[5,36],"deep":[6,38],"neural":[7,39,44],"network":[8],"acoustic":[9,65],"modeling":[10],"based":[11,85],"on":[12,51,86,103,119],"label-preserving":[13],"transformations":[14],"to":[15,75,92],"deal":[16],"with":[17,68],"sparsity.":[19],"Two":[20],"approaches,":[23],"vocal":[24],"tract":[25],"length":[26],"perturbation":[27],"(VTLP)":[28],"and":[29,42,54,95,105,116,124],"stochastic":[30],"feature":[31],"mapping":[32],"(SFM),":[33],"are":[34,49,72,101],"investigated":[35],"both":[37],"networks":[40,45],"(DNNs)":[41],"convolutional":[43],"(CNNs).":[46],"The":[47],"approaches":[48],"focused":[50],"increasing":[52],"speaker":[53],"speech":[55,121],"variations":[56],"of":[57,111],"the":[58,64,69,112],"limited":[59],"training":[60],"such":[62,76],"that":[63],"models":[66],"trained":[67],"augmented":[70],"more":[73],"robust":[74],"variations.":[77],"In":[78],"addition,":[79],"a":[80,87],"two-stage":[81],"scheme":[84],"stacked":[88],"architecture":[89],"is":[90,128],"proposed":[91],"combine":[93],"VTLP":[94],"SFM":[96],"as":[97],"complementary":[98],"approaches.":[99],"Experiments":[100],"conducted":[102],"Assamese":[104],"Haitian":[106],"Creole,":[107],"two":[108],"development":[109],"languages":[110],"IARPA":[113],"Babel":[114],"program,":[115],"improved":[117],"performance":[118],"automatic":[120],"recognition":[122],"(ASR)":[123],"keyword":[125],"search":[126],"(KWS)":[127],"reported.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":59},{"year":2020,"cited_by_count":55},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}