{"id":"https://openalex.org/W1583048384","doi":"https://doi.org/10.1109/icassp.2015.7178795","title":"Deep autoencoders augmented with phone-class feature for reverberant speech recognition","display_name":"Deep autoencoders augmented with phone-class feature for reverberant speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1583048384","doi":"https://doi.org/10.1109/icassp.2015.7178795","mag":"1583048384"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178795","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/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University Sakyo-ku, Kyoto, Japan","Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, 606-8501 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, 606-8501 Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University Sakyo-ku, Kyoto, Japan","Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, 606-8501 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, 606-8501 Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University Sakyo-ku, Kyoto, Japan","Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, 606-8501 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, 606-8501 Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"4365","last_page":"4369"},"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":0.9998999834060669,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8002574443817139},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7376987934112549},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6671277284622192},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6583677530288696},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6379356980323792},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5594714879989624},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5485145449638367},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5443382859230042},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5303265452384949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216893553733826},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5095701217651367},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47525450587272644},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45571139454841614},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44707953929901123},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.43660444021224976},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4117478132247925},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40303510427474976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07323205471038818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002574443817139},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7376987934112549},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6671277284622192},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6583677530288696},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6379356980323792},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5594714879989624},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5485145449638367},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5443382859230042},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5303265452384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216893553733826},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5095701217651367},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47525450587272644},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45571139454841614},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44707953929901123},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.43660444021224976},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4117478132247925},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40303510427474976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07323205471038818},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178795","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1973681148","https://openalex.org/W1989314204","https://openalex.org/W1993882792","https://openalex.org/W2022011789","https://openalex.org/W2025768430","https://openalex.org/W2054566816","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2082474452","https://openalex.org/W2085313529","https://openalex.org/W2089177488","https://openalex.org/W2100432131","https://openalex.org/W2100495367","https://openalex.org/W2106259503","https://openalex.org/W2107992675","https://openalex.org/W2110322414","https://openalex.org/W2110798204","https://openalex.org/W2130640611","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2157649472","https://openalex.org/W2160815625","https://openalex.org/W2168013545","https://openalex.org/W2184045248","https://openalex.org/W2296581541","https://openalex.org/W2394932179","https://openalex.org/W2403307129","https://openalex.org/W2405774341","https://openalex.org/W2408660648","https://openalex.org/W2408713104","https://openalex.org/W6676481782","https://openalex.org/W6697251715","https://openalex.org/W6713658392","https://openalex.org/W6713729801","https://openalex.org/W6713842150"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"reverberant":[3],"speech":[4,31,36],"recognition":[5,96],"based":[6,37],"on":[7,38,61,118],"front-end":[8],"processing":[9],"using":[10,146],"DAE":[11,22],"(Deep":[12,17],"AutoEncoder)":[13],"coupled":[14],"with":[15,50],"DNN":[16],"Neural":[18],"Network)":[19],"acoustic":[20,52,80],"model.":[21],"can":[23],"effectively":[24],"and":[25,100],"flexibly":[26],"learn":[27],"mapping":[28,45,57],"from":[29,108,137],"corrupted":[30],"to":[32,77],"the":[33,39,51,56,62,78,87,94,101,109,116,119,124,138,147,151],"original":[34],"clean":[35],"deep":[40],"learning":[41],"scheme.":[42],"While":[43],"this":[44],"is":[46,58,93,103,142,154],"conventionally":[47],"conducted":[48],"only":[49],"information,":[53],"we":[54,66],"presume":[55],"also":[59,143],"dependent":[60],"phone":[63],"information.":[64],"Therefore,":[65],"propose":[67],"a":[68,74,104,132],"new":[69],"scheme":[70],"(pDAE),":[71],"which":[72],"augments":[73],"phone-class":[75,88],"feature":[76,89,126],"standard":[79,139],"features":[81],"as":[82],"input.":[83],"Two":[84],"types":[85],"of":[86,98,112],"are":[90],"investigated.":[91],"One":[92],"hard":[95],"result":[97],"monophones,":[99],"other":[102],"soft":[105,148],"representation":[106,149],"derived":[107],"posterior":[110],"outputs":[111],"monophone":[113],"DNN.":[114],"In":[115],"evaluation":[117],"Reverb":[120],"Challenge":[121],"2014":[122],"task,":[123],"augmented":[125],"in":[127,131,150],"either":[128],"type":[129],"results":[130],"significant":[133],"improvement":[134],"(7-8%":[135],"relative)":[136],"DAE.":[140],"It":[141],"shown":[144],"that":[145],"training":[152],"phase":[153],"critical.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}