{"id":"https://openalex.org/W1522199561","doi":"https://doi.org/10.1186/s13634-015-0246-6","title":"Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature","display_name":"Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature","publication_year":2015,"publication_date":"2015-07-22","ids":{"openalex":"https://openalex.org/W1522199561","doi":"https://doi.org/10.1186/s13634-015-0246-6","mag":"1522199561"},"language":"en","primary_location":{"id":"doi:10.1186/s13634-015-0246-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0246-6","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0246-6","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0246-6","any_repository_has_fulltext":true},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, Kyoto, 606-8501, Japan","Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, Kyoto, 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"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, 606-8501, Japan","Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, Kyoto, 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"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, 606-8501, Japan","Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Sakyo-ku, Kyoto, 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102851028"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":{"value":1140,"currency":"GBP","value_usd":1398},"apc_paid":{"value":1140,"currency":"GBP","value_usd":1398},"fwci":3.9288,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93926924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/autoencoder","display_name":"Autoencoder","score":0.7738924026489258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7389815449714661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6101620197296143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5893219709396362},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5704341530799866},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5702205300331116},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5518046617507935},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5384058952331543},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49861574172973633},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4680456817150116},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45456886291503906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42583349347114563}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7738924026489258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7389815449714661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6101620197296143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5893219709396362},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5704341530799866},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5702205300331116},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5518046617507935},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5384058952331543},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49861574172973633},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4680456817150116},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45456886291503906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42583349347114563},{"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":2,"locations":[{"id":"doi:10.1186/s13634-015-0246-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0246-6","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0246-6","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000159408","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/201887","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/s13634-015-0246-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13634-015-0246-6","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13634-015-0246-6","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338112","display_name":"Exploratory Research for Advanced Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1522199561.pdf","grobid_xml":"https://content.openalex.org/works/W1522199561.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1554663460","https://openalex.org/W1973681148","https://openalex.org/W1989314204","https://openalex.org/W1993882792","https://openalex.org/W2022011789","https://openalex.org/W2025768430","https://openalex.org/W2042071805","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/W2136922672","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/W3031363333","https://openalex.org/W4205686602"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W2153098279","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3208304128"],"abstract_inverted_index":{"We":[0],"propose":[1,242],"an":[2],"approach":[3],"to":[4,180,198,252],"reverberant":[5,214],"speech":[6,132,136,217],"recognition":[7,137,202,271],"adopting":[8],"deep":[9,126,195],"learning":[10],"in":[11,140,159,205,218,293,297],"the":[12,114,121,131,141,156,160,169,181,187,194,199,206,211,226,231,237,253,262,269,276,284,305],"front-end":[13,115],"as":[14,16,257],"well":[15],"b":[17,31,94],"a":[18,25,34,60,63,97,109,125,174,243,249,279,298],"c":[19,41,45,111],"k-e":[20],"n":[21,35,48,53,61,64,101,110],"d":[22,62,74,87],"o":[23,46,52,65,73,76,81,100,106],"f":[24,105],"r":[26,30,33,43,80,89,93,96,104,107],"e":[27,29,32,39,40,44,58,67,70,83,86,88,90,92,95,103,112],"v":[28,66,82,91],"t":[36,50,57,71,75,84,98],"s":[37,54,56],"p":[38,79,102],"h":[42,72,85],"g":[47],"i":[49,51,77,99],"y":[55],"m,":[59],"l":[68],"m":[69,78,108],"of":[113,201,261,273,287],"network":[116],"using":[117,143],"phone-class":[118,250,263],"information.":[119,239],"At":[120],"front-end,":[122],"we":[123,229,241],"adopt":[124],"autoencoder":[127,196],"(DAE)":[128],"for":[129],"enhancing":[130],"feature":[133,191,251,264,292],"parameters,":[134],"and":[135,215,275],"is":[138,221,233,268,278],"performed":[139],"back-end":[142],"DNN-HMM":[144,165],"acoustic":[145,227,255],"models":[146],"trained":[147,167,185],"on":[148,168,186,236],"multi-condition":[149,170],"data.":[150,189],"The":[151,164,290],"system":[152,166,184],"was":[153],"evaluated":[154],"through":[155],"ASR":[157],"task":[158],"Reverb":[161],"Challenge":[162],"2014.":[163],"training":[171],"set":[172],"achieved":[173],"conspicuously":[175],"higher":[176],"word":[177],"accuracy":[178,203],"compared":[179],"MLLR-adapted":[182],"GMM-HMM":[183],"same":[188],"Furthermore,":[190],"enhancement":[192],"with":[193,225],"contributed":[197],"improvement":[200,300],"especially":[204],"more":[207],"adverse":[208],"conditions.":[209],"While":[210],"mapping":[212,232],"between":[213],"clean":[216],"DAE-based":[219],"dereverberation":[220],"conventionally":[222],"conducted":[223],"only":[224],"information,":[228],"presume":[230],"also":[234],"dependent":[235],"phone":[238],"Therefore,":[240],"new":[244],"scheme":[245],"(pDAE),":[246],"which":[247],"augments":[248],"standard":[254,306],"features":[256],"input.":[258],"Two":[259],"types":[260],"are":[265],"investigated.":[266],"One":[267],"hard":[270],"result":[272],"monophones,":[274],"other":[277],"soft":[280],"representation":[281],"derived":[282],"from":[283,304],"posterior":[285],"outputs":[286],"monophone":[288],"DNN.":[289],"augmented":[291],"either":[294],"type":[295],"results":[296],"significant":[299],"(7\u20138":[301],"%":[302],"relative)":[303],"DAE.":[307]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}