{"id":"https://openalex.org/W2292655135","doi":"https://doi.org/10.1109/asru.2015.7404840","title":"Improving robustness against reverberation for automatic speech recognition","display_name":"Improving robustness against reverberation for automatic speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2292655135","doi":"https://doi.org/10.1109/asru.2015.7404840","mag":"2292655135"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058481276","display_name":"Julien van Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien Van Hout","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396385","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-1707-0163"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Graciarena","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112857367","display_name":"Horacio Franco","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Horacio Franco","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitra Vergyri","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6996,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86411696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"49","issue":null,"first_page":"525","last_page":"532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9983000159263611,"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/reverberation","display_name":"Reverberation","score":0.8666833639144897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912688851356506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.760662317276001},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7282218337059021},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6547445058822632},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6010967493057251},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47240394353866577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44502002000808716},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4310382306575775},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4292071759700775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4259575605392456},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4122934937477112},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4116900563240051},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.20907577872276306},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09719353914260864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09625214338302612}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8666833639144897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912688851356506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.760662317276001},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7282218337059021},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6547445058822632},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6010967493057251},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47240394353866577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44502002000808716},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4310382306575775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4292071759700775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4259575605392456},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4122934937477112},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4116900563240051},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.20907577872276306},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09719353914260864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09625214338302612},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/asru.2015.7404840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1498638354","https://openalex.org/W1515932869","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1904457459","https://openalex.org/W1981730446","https://openalex.org/W1989314204","https://openalex.org/W1993882792","https://openalex.org/W2037057286","https://openalex.org/W2061778110","https://openalex.org/W2062164080","https://openalex.org/W2075012882","https://openalex.org/W2079623482","https://openalex.org/W2097978681","https://openalex.org/W2102072896","https://openalex.org/W2108072369","https://openalex.org/W2110322414","https://openalex.org/W2112739286","https://openalex.org/W2121173708","https://openalex.org/W2125471631","https://openalex.org/W2140979961","https://openalex.org/W2145692202","https://openalex.org/W2150769028","https://openalex.org/W2155273149","https://openalex.org/W2158273884","https://openalex.org/W2187325407","https://openalex.org/W2289731793","https://openalex.org/W2289912446","https://openalex.org/W2292414329","https://openalex.org/W2293535060","https://openalex.org/W2295098554","https://openalex.org/W2394932179","https://openalex.org/W2395321025","https://openalex.org/W2403277918","https://openalex.org/W2406171445","https://openalex.org/W2474824677","https://openalex.org/W4249052411","https://openalex.org/W6631362777","https://openalex.org/W6674334065","https://openalex.org/W6686982758","https://openalex.org/W6697089127","https://openalex.org/W6712234020","https://openalex.org/W6713360458","https://openalex.org/W6713487325"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W4401069787","https://openalex.org/W1499578372","https://openalex.org/W2964954556"],"abstract_inverted_index":{"Reverberation":[0],"is":[1,177],"a":[2,131],"phenomenon":[3],"observed":[4],"in":[5,15,18,101,116],"almost":[6],"all":[7,163,167],"enclosed":[8],"environments.":[9,103],"Human":[10],"listeners":[11],"rarely":[12],"experience":[13],"problems":[14],"comprehending":[16],"speech":[17,23,49,100],"reverberant":[19,102],"environments,":[20],"but":[21],"automatic":[22],"recognition":[24],"(ASR)":[25],"systems":[26,55,108,123,161],"often":[27],"suffer":[28],"increased":[29],"error":[30,118],"rates":[31,119],"under":[32],"such":[33],"conditions.":[34,169],"In":[35,69],"this":[36],"work,":[37],"we":[38,77,154,171],"explore":[39,78],"the":[40,61,65,143,148,159],"role":[41],"of":[42,182],"robust":[43,56,111],"acoustic":[44,95],"features":[45,112],"motivated":[46],"by":[47,75],"human":[48],"perception":[50],"studies,":[51],"for":[52,64,97,162],"building":[53],"ASR":[54],"to":[57,122,156],"reverberation":[58],"effects.":[59],"Using":[60],"dataset":[62],"distributed":[63],"\"Automatic":[66],"Speech":[67],"Recognition":[68],"Reverberant":[70],"Environments\"":[71],"(ASpIRE-2015)":[72],"challenge":[73],"organized":[74],"IARPA,":[76],"Gaussian":[79],"mixture":[80],"models":[81,96],"(GMMs),":[82],"deep":[83,89],"neural":[84,90,135],"nets":[85],"(DNNs)":[86],"and":[87,150],"convolutional":[88],"networks":[91],"(CDNN)":[92],"as":[93],"candidate":[94],"recognizing":[98],"continuous":[99],"We":[104,129],"demonstrate":[105],"that":[106,139,173],"DNN-based":[107],"trained":[109,124],"with":[110,125],"offer":[113],"significant":[114],"reduction":[115,176],"word":[117],"(WERs)":[120],"compared":[121],"baseline":[126],"mel-filterbank":[127],"features.":[128],"present":[130],"novel":[132],"time-frequency":[133],"convolution":[134,141],"net":[136],"(TFCNN)":[137],"framework":[138],"performs":[140],"on":[142],"feature":[144,164],"space":[145],"across":[146,166],"both":[147],"time":[149],"frequency":[151],"scales,":[152],"which":[153],"found":[155],"consistently":[157],"outperform":[158],"CDNN":[160],"sets":[165],"testing":[168],"Finally,":[170],"show":[172],"further":[174],"WER":[175],"achievable":[178],"through":[179],"system":[180],"fusion":[181],"n-best":[183],"lists":[184],"from":[185],"multiple":[186],"systems.":[187]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}