{"id":"https://openalex.org/W2696967604","doi":"https://doi.org/10.1109/icassp.2017.7953152","title":"A study on data augmentation of reverberant speech for robust speech recognition","display_name":"A study on data augmentation of reverberant speech for robust speech recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2696967604","doi":"https://doi.org/10.1109/icassp.2017.7953152","mag":"2696967604"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["Huawei Noah's Ark Research Lab, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Research Lab, Hong Kong, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":["Center for Language and Speech Processing &"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing &","institution_ids":["https://openalex.org/I4210098364"]}]},{"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"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Center for Language and Speech Processing &","Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing &","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing &","Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing &","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":922,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5220","last_page":"5224"},"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":0.998199999332428,"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/robustness","display_name":"Robustness (evolution)","score":0.8160948753356934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8128294944763184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7193701267242432},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5522680878639221},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.49513712525367737},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4913925230503082},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4641168713569641},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4294564723968506},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41052964329719543},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3702901005744934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.301556259393692},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06329023838043213}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8160948753356934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128294944763184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7193701267242432},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5522680878639221},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.49513712525367737},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4913925230503082},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4641168713569641},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4294564723968506},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41052964329719543},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3702901005744934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.301556259393692},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06329023838043213},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1495076553","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1989314204","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2117678320","https://openalex.org/W2136439176","https://openalex.org/W2136682440","https://openalex.org/W2143612262","https://openalex.org/W2219249508","https://openalex.org/W2245569228","https://openalex.org/W2288817436","https://openalex.org/W2289912446","https://openalex.org/W2292733088","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2510616059","https://openalex.org/W2514741789","https://openalex.org/W2964138484","https://openalex.org/W2970850616","https://openalex.org/W6688816777","https://openalex.org/W6690610466"],"related_works":["https://openalex.org/W2992378684","https://openalex.org/W4285322112","https://openalex.org/W2964829415","https://openalex.org/W4292794239","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W2186896963","https://openalex.org/W4361192867","https://openalex.org/W3143423642"],"abstract_inverted_index":{"The":[0],"environmental":[1],"robustness":[2],"of":[3,25,50,69],"DNN-based":[4],"acoustic":[5,99],"models":[6,100],"can":[7,60,85,127],"be":[8,61,86],"significantly":[9],"improved":[10],"by":[11],"using":[12,51,80],"multi-condition":[13],"training":[14],"data.":[15],"However,":[16],"as":[17,57],"data":[18,40],"collection":[19],"is":[20,29],"a":[21,30,39],"costly":[22],"proposition,":[23],"simulation":[24],"the":[26,48,67,76,97,106,115],"desired":[27],"conditions":[28],"frequently":[31],"adopted":[32],"strategy.":[33],"In":[34],"this":[35],"paper":[36],"we":[37,94],"detail":[38],"augmentation":[41],"approach":[42,121],"for":[43],"far-field":[44],"ASR.":[45],"We":[46,73,118],"examine":[47],"impact":[49],"simulated":[52,81],"room":[53],"impulse":[54],"responses":[55],"(RIRs),":[56],"real":[58,83],"RIRs":[59,84],"difficult":[62],"to":[63],"acquire,":[64],"and":[65,82],"also":[66,110],"effect":[68],"adding":[70],"point-source":[71,89],"noises.":[72],"find":[74],"that":[75,96],"performance":[77],"gap":[78],"between":[79],"eliminated":[87],"when":[88],"noises":[90],"are":[91],"added.":[92],"Further":[93],"show":[95],"trained":[98],"not":[101],"only":[102],"perform":[103],"well":[104],"in":[105,114],"distant-talking":[107],"scenario":[108],"but":[109],"provide":[111],"better":[112],"results":[113],"close-talking":[116],"scenario.":[117],"evaluate":[119],"our":[120],"on":[122],"several":[123],"LVCSR":[124],"tasks":[125],"which":[126],"adequately":[128],"represent":[129],"both":[130],"scenarios.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":43},{"year":2025,"cited_by_count":113},{"year":2024,"cited_by_count":130},{"year":2023,"cited_by_count":110},{"year":2022,"cited_by_count":149},{"year":2021,"cited_by_count":134},{"year":2020,"cited_by_count":113},{"year":2019,"cited_by_count":83},{"year":2018,"cited_by_count":40},{"year":2017,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}