{"id":"https://openalex.org/W2296581541","doi":"https://doi.org/10.21437/interspeech.2013-267","title":"Reverberant speech recognition based on denoising autoencoder","display_name":"Reverberant speech recognition based on denoising autoencoder","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2296581541","doi":"https://doi.org/10.21437/interspeech.2013-267","mag":"2296581541"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-267","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5007884618","display_name":"Takaaki Ishii","orcid":"https://orcid.org/0000-0001-6690-7834"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Takaaki Ishii","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006498407","display_name":"Hiroki Komiyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroki Komiyama","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110633678","display_name":"Yasuo Horiuchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuo Horiuchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112035972","display_name":"Shingo Kuroiwa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shingo Kuroiwa","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007884618"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.8625,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.9916979,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3512","last_page":"3516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.775274395942688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.718464195728302},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6932724118232727},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5597016215324402},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5518244504928589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5214844942092896},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4785895347595215},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2137640118598938},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14206162095069885}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.775274395942688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718464195728302},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6932724118232727},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5597016215324402},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5518244504928589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214844942092896},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4785895347595215},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2137640118598938},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14206162095069885},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-267","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50483511","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100801606","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W349097443","https://openalex.org/W1982728343","https://openalex.org/W1993882792","https://openalex.org/W2005522781","https://openalex.org/W2100495367","https://openalex.org/W2107992675","https://openalex.org/W2116064496","https://openalex.org/W2128621997","https://openalex.org/W2145094598","https://openalex.org/W2148154194","https://openalex.org/W2168013545","https://openalex.org/W2172203831","https://openalex.org/W2290318471","https://openalex.org/W2316564661","https://openalex.org/W2404637451"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W3037110488"],"abstract_inverted_index":{"Denoising":[0,176],"autoencoder":[1,95],"is":[2,53,78,115,130,143,151,161],"applied":[3],"to":[4,13,23,39,55],"reverberant":[5,178],"speech":[6,16,28,69,86,159,179,185],"recognition":[7,118,160],"as":[8,80],"a":[9,30,41,46,146,154],"noise":[10],"robust":[11],"front-end":[12,97],"reconstruct":[14],"clean":[15],"spectrum":[17],"from":[18],"noisy":[19],"input.":[20],"In":[21],"order":[22],"capture":[24],"context":[25],"effects":[26],"of":[27,32,48,61,138,167],"sounds,":[29],"window":[31],"multiple":[33],"short-windowed":[34],"spectral":[35],"frames":[36],"are":[37,72],"concatenated":[38],"form":[40],"single":[42],"input":[43],"vector.":[44],"Additionally,":[45],"combination":[47],"short":[49,126],"and":[50,127,164],"long-term":[51,111,128],"spectra":[52,101,129],"investigated":[54],"properly":[56],"handle":[57],"long":[58],"impulse":[59],"response":[60],"reverberation":[62],"while":[63],"keeping":[64],"necessary":[65],"time":[66],"resolution":[67],"for":[68,84,132],"recognition.":[70,87],"Experiments":[71],"performed":[73,163],"using":[74,98,124],"the":[75,92,99,110,121,125,133,139,165,168],"CENSREC-4dataset":[76],"that":[77,91],"designed":[79],"an":[81],"evaluation":[82],"framework":[83],"distant-talking":[85,184],"Experimental":[88],"results":[89,104],"show":[90],"proposed":[93,122,169],"denoising":[94],"based":[96,149],"shortwindowed":[100],"gives":[102],"better":[103],"than":[105],"conventional":[106],"methods.":[107],"By":[108],"combining":[109],"spectra,":[112],"further":[113],"improvement":[114],"obtained.":[116],"The":[117],"accuracy":[119],"by":[120],"method":[123,170],"97.0%":[131],"open":[134],"condition":[135],"test":[136],"set":[137],"dataset,":[140],"whereas":[141],"it":[142],"87.8%":[144],"when":[145],"multicondition":[147],"training":[148],"baseline":[150],"used.":[152],"As":[153],"supplemental":[155],"experiment,":[156],"large":[157],"vocabulary":[158],"also":[162],"effectiveness":[166],"has":[171],"been":[172],"confirmed.":[173],"Index":[174],"Terms:":[175],"autoencoder,":[177],"recognition,":[180,186],"restricted":[181],"Boltzmann":[182],"machine,":[183],"CENSREC-4":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}