{"id":"https://openalex.org/W1557160870","doi":"https://doi.org/10.1109/icassp.2015.7178794","title":"Far-field speech recognition using CNN-DNN-HMM with convolution in time","display_name":"Far-field speech recognition using CNN-DNN-HMM with convolution in time","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1557160870","doi":"https://doi.org/10.1109/icassp.2015.7178794","mag":"1557160870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178794","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":"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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["Graduate School of Engineering, Osaka University, Osaka, Japan","NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4360","last_page":"4364"},"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":0.9997000098228455,"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":0.9976999759674072,"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":0.8421592116355896},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7918649315834045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.744539737701416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7249904274940491},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7237743139266968},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5715445280075073},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.542943000793457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5034882426261902},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4946455657482147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4477435052394867},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40664222836494446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17424499988555908},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1115366518497467}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8421592116355896},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7918649315834045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.744539737701416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249904274940491},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7237743139266968},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5715445280075073},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.542943000793457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5034882426261902},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4946455657482147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4477435052394867},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40664222836494446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17424499988555908},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1115366518497467},{"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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178794","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":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1512562331","https://openalex.org/W1973669708","https://openalex.org/W1981617403","https://openalex.org/W1983812858","https://openalex.org/W1985261152","https://openalex.org/W1987841215","https://openalex.org/W1989314204","https://openalex.org/W1992912377","https://openalex.org/W1995562189","https://openalex.org/W2006783645","https://openalex.org/W2039716246","https://openalex.org/W2042071805","https://openalex.org/W2042141988","https://openalex.org/W2069431997","https://openalex.org/W2103088716","https://openalex.org/W2117518720","https://openalex.org/W2137644731","https://openalex.org/W2147706354","https://openalex.org/W2147768505","https://openalex.org/W2148898720","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2187325407","https://openalex.org/W2188162373","https://openalex.org/W2188183693","https://openalex.org/W2762693443","https://openalex.org/W2962719052","https://openalex.org/W6686978693","https://openalex.org/W6686982758","https://openalex.org/W6745258804","https://openalex.org/W6941384618"],"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/W2964954556","https://openalex.org/W3088721469"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"in":[2,35,62,91,123],"speech":[3,37,57],"recognition":[4,38],"have":[5],"shown":[6,120],"that":[7,18,77],"the":[8,31,48,127,139],"performance":[9],"of":[10,19,33,138,141],"convolutional":[11],"neural":[12,23],"networks":[13,24],"(CNNs)":[14],"is":[15,119,145],"superior":[16],"to":[17,56,64,104,121],"fully":[20,83],"connected":[21,84],"deep":[22],"(DNNs).":[25],"In":[26],"this":[27,109],"paper,":[28],"we":[29,59],"explore":[30],"use":[32,140],"CNNs":[34],"far-field":[36],"for":[39],"dealing":[40],"with":[41,81,94,111,116],"reverberation,":[42],"which":[43,114],"blurs":[44],"spectral":[45],"energies":[46],"along":[47],"time":[49,63,89],"axis.":[50],"Unlike":[51],"most":[52],"previous":[53],"CNN":[54,79],"applications":[55],"recognition,":[58],"consider":[60],"convolution":[61,143],"examine":[65],"whether":[66],"it":[67],"provides":[68],"an":[69],"improved":[70],"reverberation":[71],"modelling":[72],"capability.":[73],"Experimental":[74],"results":[75],"show":[76],"a":[78,82,98],"coupled":[80],"DNN":[85,99],"can":[86],"model":[87],"short":[88],"correlations":[90],"feature":[92],"vectors":[93],"fewer":[95],"parameters":[96],"than":[97],"and":[100],"thus":[101],"generalise":[102],"better":[103],"unseen":[105],"test":[106],"environments.":[107],"Combining":[108],"approach":[110],"signal-space":[112],"dereverberation,":[113],"copes":[115],"long-term":[117],"correlations,":[118],"result":[122],"further":[124],"improvement,":[125],"where":[126],"gains":[128],"from":[129],"both":[130],"approaches":[131],"are":[132],"almost":[133],"additive.":[134],"An":[135],"initial":[136],"investigation":[137],"restricted":[142],"forms":[144],"also":[146],"undertaken.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}