{"id":"https://openalex.org/W1509793305","doi":"https://doi.org/10.1109/icassp.2015.7178831","title":"Data augmentation for deep convolutional neural network acoustic modeling","display_name":"Data augmentation for deep convolutional neural network acoustic modeling","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1509793305","doi":"https://doi.org/10.1109/icassp.2015.7178831","mag":"1509793305"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY, USA","institution_ids":[]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"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/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"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/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY, USA","institution_ids":[]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":8.0348,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.973229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4545","last_page":"4549"},"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":0.9993000030517578,"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":0.9988999962806702,"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":0.8292608261108398},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7808330655097961},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6281701922416687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.539508044719696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5291662216186523},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5259922742843628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5105656385421753},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47304409742355347},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4595798850059509},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4489596486091614},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4421907067298889},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4206061065196991},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11262285709381104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292608261108398},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7808330655097961},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6281701922416687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.539508044719696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5291662216186523},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5259922742843628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5105656385421753},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47304409742355347},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4595798850059509},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4489596486091614},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4421907067298889},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4206061065196991},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11262285709381104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1654807615","https://openalex.org/W2002342963","https://openalex.org/W2039285212","https://openalex.org/W2099621636","https://openalex.org/W2106554350","https://openalex.org/W2112796928","https://openalex.org/W2146871184","https://openalex.org/W2155117693","https://openalex.org/W2156163116","https://openalex.org/W2163605009","https://openalex.org/W2164931619","https://openalex.org/W2170794967","https://openalex.org/W2397450537","https://openalex.org/W2403195671","https://openalex.org/W2962719052","https://openalex.org/W6636948317","https://openalex.org/W6675409298","https://openalex.org/W6684191040","https://openalex.org/W6712539218"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W1748856376","https://openalex.org/W2046073792","https://openalex.org/W3000197790","https://openalex.org/W4285322112","https://openalex.org/W3158596343","https://openalex.org/W4292794239","https://openalex.org/W4385572030"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"data":[3,55],"augmentation":[4,56],"based":[5],"on":[6,80],"label-preserving":[7],"transformations":[8],"for":[9],"deep":[10],"convolutional":[11],"neural":[12],"network":[13],"(CNN)":[14],"acoustic":[15],"modeling":[16],"to":[17,64],"deal":[18],"with":[19,38,46,58],"limited":[20,82],"training":[21,35],"data.":[22],"We":[23],"show":[24],"how":[25],"stochastic":[26],"feature":[27],"mapping":[28],"(SFM)":[29],"can":[30],"be":[31],"carried":[32],"out":[33],"when":[34],"CNN":[36],"models":[37],"log-Mel":[39],"features":[40],"as":[41,69],"input":[42],"and":[43,67],"compare":[44],"it":[45],"vocal":[47],"tract":[48],"length":[49],"perturbation":[50],"(VTLP).":[51],"Furthermore,":[52],"a":[53,59],"two-stage":[54],"scheme":[57],"stacked":[60],"architecture":[61],"is":[62],"proposed":[63],"combine":[65],"VTLP":[66],"SFM":[68],"complementary":[70],"approaches.":[71],"Improved":[72],"performance":[73],"has":[74],"been":[75],"observed":[76],"in":[77,89],"experiments":[78],"conducted":[79],"the":[81,90],"language":[83],"pack":[84],"(LLP)":[85],"of":[86],"Haitian":[87],"Creole":[88],"IARPA":[91],"Babel":[92],"program.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3}],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}