{"id":"https://openalex.org/W2061778110","doi":"https://doi.org/10.1109/slt.2014.7078633","title":"Deep convolutional nets and robust features for reverberation-robust speech recognition","display_name":"Deep convolutional nets and robust features for reverberation-robust speech recognition","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2061778110","doi":"https://doi.org/10.1109/slt.2014.7078633","mag":"2061778110"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/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":true,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066920453","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-2950-693X"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112857367","display_name":"Horacio Franco","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Horacio Franco","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091201226"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":2.0379,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87309028,"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":"548","last_page":"553"},"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":0.9998000264167786,"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":0.9984999895095825,"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":0.8961549997329712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8073326349258423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7862361669540405},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6800599694252014},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6712757349014282},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5304731130599976},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5233489871025085},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5006091594696045},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4836888909339905},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4747225046157837},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47135061025619507},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4391981065273285},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42907750606536865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42370879650115967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3219575881958008},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1667994260787964},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10374897718429565},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09096664190292358},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08875823020935059}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8961549997329712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8073326349258423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862361669540405},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6800599694252014},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6712757349014282},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5304731130599976},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5233489871025085},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5006091594696045},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4836888909339905},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4747225046157837},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47135061025619507},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4391981065273285},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42907750606536865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42370879650115967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3219575881958008},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1667994260787964},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10374897718429565},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09096664190292358},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08875823020935059},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/slt.2014.7078633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1498638354","https://openalex.org/W1515932869","https://openalex.org/W1904457459","https://openalex.org/W1981730446","https://openalex.org/W1989314204","https://openalex.org/W1993882792","https://openalex.org/W2024490156","https://openalex.org/W2079623482","https://openalex.org/W2108072369","https://openalex.org/W2110322414","https://openalex.org/W2112739286","https://openalex.org/W2114537326","https://openalex.org/W2125471631","https://openalex.org/W2130722890","https://openalex.org/W2140979961","https://openalex.org/W2147166770","https://openalex.org/W2150769028","https://openalex.org/W2155273149","https://openalex.org/W2158273884","https://openalex.org/W2187325407","https://openalex.org/W2395321025","https://openalex.org/W2398177287","https://openalex.org/W2406171445","https://openalex.org/W4249052411","https://openalex.org/W6686982758","https://openalex.org/W6712234020","https://openalex.org/W6712709601","https://openalex.org/W6713360458"],"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/W2944691285","https://openalex.org/W2114026179","https://openalex.org/W2108641942"],"abstract_inverted_index":{"While":[0],"human":[1,42],"listeners":[2],"can":[3],"understand":[4],"speech":[5,28,43,59],"in":[6,47,60,82,91,131,134],"reverberant":[7,62,83],"conditions,":[8,84],"indicating":[9],"that":[10],"the":[11,70,76,98,127],"auditory":[12],"system":[13,67,125,129],"is":[14,112],"robust":[15,37],"to":[16,21,97],"such":[17],"degradations,":[18],"reverberation":[19,108],"leads":[20],"high":[22],"word":[23,92],"error":[24,93],"rates":[25,94],"for":[26,45,56,103],"automatic":[27],"recognition":[29],"(ASR)":[30],"systems.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,85],"present":[36],"acoustic":[38,54],"features":[39,102,117],"motivated":[40],"by":[41],"perception":[44],"use":[46],"a":[48,61,65,87],"convolutional":[49],"deep":[50],"neural":[51],"network":[52],"(CDNN)-based":[53],"model":[55],"recognizing":[57],"continuous":[58],"condition.":[63],"Using":[64],"single-feature":[66],"trained":[68],"with":[69],"single":[71,135],"channel":[72,136],"data":[73],"distributed":[74],"through":[75],"REVERB":[77],"2014":[78],"challenge":[79,133],"on":[80],"ASR":[81],"show":[86],"substantial":[88],"relative":[89],"reduction":[90,111],"(WERs)":[95],"compared":[96],"conventional":[99],"filterbank":[100],"energy-based":[101],"single-channel":[104],"simulated":[105],"and":[106,118],"real":[107],"conditions.":[109],"The":[110,123],"more":[113],"pronounced":[114],"when":[115],"multiple":[116],"systems":[119],"were":[120],"combined":[121],"together.":[122],"proposed":[124],"outperforms":[126],"best":[128],"reported":[130],"REVERB-2014":[132],"full-batch":[137],"processing":[138],"task.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
