{"id":"https://openalex.org/W2407080277","doi":"https://doi.org/10.21437/interspeech.2015-711","title":"Audio augmentation for speech recognition","display_name":"Audio augmentation for speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2407080277","doi":"https://doi.org/10.21437/interspeech.2015-711","mag":"2407080277"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-711","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tom Ko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038062913"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":38.2135,"has_fulltext":false,"cited_by_count":1138,"citation_normalized_percentile":{"value":0.99885176,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3586","last_page":"3589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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":0.9995999932289124,"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/speech-recognition","display_name":"Speech recognition","score":0.7313065528869629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259602546691895},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.448797345161438},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3245111107826233},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.251962274312973}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7313065528869629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259602546691895},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.448797345161438},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3245111107826233},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.251962274312973}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-711","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1762484328","https://openalex.org/W1922655562","https://openalex.org/W1989674786","https://openalex.org/W2026369565","https://openalex.org/W2039285212","https://openalex.org/W2085628288","https://openalex.org/W2093231248","https://openalex.org/W2099621636","https://openalex.org/W2148154194","https://openalex.org/W2168510624","https://openalex.org/W2169272853","https://openalex.org/W2184343439","https://openalex.org/W2250357346","https://openalex.org/W2402146185"],"related_works":["https://openalex.org/W2539919382","https://openalex.org/W22517275","https://openalex.org/W2589081144","https://openalex.org/W2042419400","https://openalex.org/W2064347532","https://openalex.org/W189256204","https://openalex.org/W4387294562","https://openalex.org/W2981428355","https://openalex.org/W2131711534","https://openalex.org/W2122924390"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,29,103],"is":[2,42],"a":[3,70,105],"common":[4],"strategy":[5],"adopted":[6],"to":[7,43,77,94,97],"increase":[8],"the":[9,20,34,45,48,55,99,119],"quantity":[10],"of":[11,19,47,54,61,101,107,114],"training":[12,88],"data,":[13],"avoid":[14],"overfitting":[15],"and":[16,64],"improve":[17],"robustness":[18],"models.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,39],"investigate":[26],"audio-level":[27],"speech":[28],"methods":[30],"which":[31],"directly":[32],"process":[33],"raw":[35],"signal.":[36],"The":[37,66],"method":[38],"particularly":[40],"recommend":[41],"change":[44],"speed":[46,59],"audio":[49,102],"signal,":[50],"producing":[51],"3":[52],"versions":[53],"original":[56],"signal":[57],"with":[58,87],"factors":[60],"0.9,":[62],"1.0":[63],"1.1.":[65],"proposed":[67],"technique":[68],"has":[69],"low":[71],"implementation":[72],"cost,":[73],"making":[74],"it":[75],"easy":[76],"adopt.":[78],"We":[79],"present":[80],"results":[81],"on":[82],"4":[83,120],"different":[84],"LVCSR":[85],"tasks":[86],"data":[89,108],"ranging":[90],"from":[91],"100":[92],"hours":[93],"1000":[95],"hours,":[96],"examine":[98],"effectiveness":[100],"in":[104],"variety":[106],"scenarios.":[109],"An":[110],"average":[111],"relative":[112],"improvement":[113],"4.3%":[115],"was":[116],"observed":[117],"across":[118],"tasks.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":82},{"year":2024,"cited_by_count":81},{"year":2023,"cited_by_count":134},{"year":2022,"cited_by_count":150},{"year":2021,"cited_by_count":234},{"year":2020,"cited_by_count":190},{"year":2019,"cited_by_count":125},{"year":2018,"cited_by_count":68},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}