{"id":"https://openalex.org/W2395263859","doi":"https://doi.org/10.21437/interspeech.2015-526","title":"Speech dereverberation using long short-term memory","display_name":"Speech dereverberation using long short-term memory","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2395263859","doi":"https://doi.org/10.21437/interspeech.2015-526","mag":"2395263859"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2435","last_page":"2439"},"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":0.9998000264167786,"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":0.9977999925613403,"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/term","display_name":"Term (time)","score":0.7168174982070923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6700946688652039},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.554069459438324},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.5010855197906494},{"id":"https://openalex.org/keywords/short-term-memory","display_name":"Short-term memory","score":0.4393366873264313},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14372768998146057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13703492283821106},{"id":"https://openalex.org/keywords/working-memory","display_name":"Working memory","score":0.09131330251693726},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.09114208817481995},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.08947306871414185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08250710368156433}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7168174982070923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700946688652039},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.554069459438324},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.5010855197906494},{"id":"https://openalex.org/C179226034","wikidata":"https://www.wikidata.org/wiki/Q18599","display_name":"Short-term memory","level":4,"score":0.4393366873264313},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14372768998146057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13703492283821106},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.09131330251693726},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.09114208817481995},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.08947306871414185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08250710368156433},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1583048384","https://openalex.org/W1899504021","https://openalex.org/W1973681148","https://openalex.org/W1989314204","https://openalex.org/W2005708641","https://openalex.org/W2040940879","https://openalex.org/W2054566816","https://openalex.org/W2061436640","https://openalex.org/W2064675550","https://openalex.org/W2100432131","https://openalex.org/W2100495367","https://openalex.org/W2107992675","https://openalex.org/W2110322414","https://openalex.org/W2110798204","https://openalex.org/W2130640611","https://openalex.org/W2130942839","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2157649472","https://openalex.org/W2168013545","https://openalex.org/W2184045248","https://openalex.org/W2293634267","https://openalex.org/W2294797155","https://openalex.org/W2296581541","https://openalex.org/W2338600138","https://openalex.org/W2394662942","https://openalex.org/W2394932179","https://openalex.org/W2404974730","https://openalex.org/W2405774341","https://openalex.org/W2406392101","https://openalex.org/W2408660648","https://openalex.org/W2408713104","https://openalex.org/W2408752871"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W4225519494","https://openalex.org/W2323713234","https://openalex.org/W3155820633"],"abstract_inverted_index":{"Recently,":[0],"neural":[1],"networks":[2],"have":[3],"been":[4],"used":[5],"for":[6],"not":[7,29],"only":[8,189],"phone":[9,162],"recognition":[10,135],"but":[11],"also":[12],"denoising":[13,19],"and":[14,53,123,157],"dereverberation.":[15],"However,":[16],"the":[17,25,46,50,54,60,63,78,83,88,95,98,104,107,110,114,120,128,133,138,145,149,152,158,161,175,184],"conventional":[18],"deep":[20],"autoencoder":[21,108,130],"(DAE)":[22,201],"based":[23],"on":[24,94],"feed-forward":[26],"structure":[27],"is":[28,85,177,188],"capable":[30],"of":[31,37,62,82,90,97,106,113,127,141,151,160,170,181,186],"handling":[32],"very":[33],"long":[34,64,76],"speech":[35,100,134],"frames":[36,116],"reverberation.":[38],"LSTM":[39,129,146],"can":[40],"be":[41],"effectively":[42],"trained":[43],"to":[44,179],"reduce":[45],"average":[47],"error":[48],"between":[49],"enhanced":[51],"signal":[52,57],"original":[55],"clean":[56],"by":[58,155],"considering":[59,74],"effect":[61,89],"past":[65,115],"time":[66,81],"frames.":[67],"In":[68,132],"this":[69,125],"paper,":[70],"we":[71,102],"demonstrate":[72],"that":[73,180],"as":[75,77,117,119],"maximum":[79],"reverberation":[80,91],"database":[84],"effective.":[86],"Since":[87],"varies":[92],"depending":[93],"phone-class":[96,111],"whole":[99],"context,":[101],"augment":[103],"input":[105],"with":[109,174],"information":[112],"well":[118],"current":[121],"frame":[122],"call":[124],"version":[126],"pLSTM.":[131],"experiment":[136],"using":[137],"data":[139],"set":[140],"Reverb":[142],"Challenge":[143],"2014,":[144],"front-end":[147],"reduced":[148],"WER":[150],"multicondition":[153],"DNN-HMM":[154],"14.5%,":[156],"use":[159],"class":[163],"feature":[164],"yielded":[165],"in":[166],"pLSTM":[167,176],"further":[168],"improvement":[169],"7.5%.":[171],"The":[172],"performance":[173],"comparable":[178],"pDAE,":[182],"while":[183],"number":[185],"parameters":[187],"1/25-1/8.":[190],"Index":[191],"Terms:":[192],"Speech":[193],"Dereverberation,":[194],"Long":[195],"Short-Term":[196],"Memory":[197],"(LSTM),":[198],"Deep":[199],"Autoencoder":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}