{"id":"https://openalex.org/W2124248639","doi":"https://doi.org/10.1186/1687-4722-2014-13","title":"Single-channel dereverberation by feature mapping using cascade neural networks for robust distant speaker identification and speech recognition","display_name":"Single-channel dereverberation by feature mapping using cascade neural networks for robust distant speaker identification and speech recognition","publication_year":2014,"publication_date":"2014-04-10","ids":{"openalex":"https://openalex.org/W2124248639","doi":"https://doi.org/10.1186/1687-4722-2014-13","mag":"2124248639"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2014-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-13","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-13","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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 Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-13","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","[Dept. of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"[Dept. of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan]","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109057821","display_name":"Kazumasa Yamamoto","orcid":"https://orcid.org/0009-0005-4085-0741"},"institutions":[{"id":"https://openalex.org/I131361393","display_name":"National Institute of Technology, Toyota College","ror":"https://ror.org/01nw25822","country_code":"JP","type":"education","lineage":["https://openalex.org/I131361393"]},{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazumasa Yamamoto","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","Department of Information and Computer Engineering, Toyota National College of Technology, Toyota, Aichi, 471-8525, Japan","Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan","Department of Information and Computer Engineering, Toyota National College of Technology, Toyota, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Department of Information and Computer Engineering, Toyota National College of Technology, Toyota, Aichi, 471-8525, Japan","institution_ids":["https://openalex.org/I131361393"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Department of Information and Computer Engineering, Toyota National College of Technology, Toyota, Japan","institution_ids":["https://openalex.org/I131361393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018428974","display_name":"Seiichi Nakagawa","orcid":"https://orcid.org/0000-0002-6533-5536"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiichi Nakagawa","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","[Dept. of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"[Dept. of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan]","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082272880"],"corresponding_institution_ids":["https://openalex.org/I136259955"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.8965,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91833401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2014","issue":"1","first_page":null,"last_page":null},"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":0.9980999827384949,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7461851835250854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7375715374946594},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7319687008857727},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6229683756828308},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.580945611000061},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.580907940864563},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5577634572982788},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5005900859832764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4697079062461853},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4562557339668274},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4506816267967224},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4411674439907074},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4389512538909912},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38956671953201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461851835250854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7375715374946594},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7319687008857727},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6229683756828308},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.580945611000061},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.580907940864563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5577634572982788},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5005900859832764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4697079062461853},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4562557339668274},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4506816267967224},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4411674439907074},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4389512538909912},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38956671953201294},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/1687-4722-2014-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-13","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-13","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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 Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2014-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-13","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-13","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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 Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G257163487","display_name":"A study of automatic English caption generation  for Japanese lecture speech","funder_award_id":"25280062","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3535035130","display_name":"Study on an Electronic Note-Taking Support System using Speech and Language Processing Technologies","funder_award_id":"26282049","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2124248639.pdf","grobid_xml":"https://content.openalex.org/works/W2124248639.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W2195354","https://openalex.org/W3189630","https://openalex.org/W96504731","https://openalex.org/W253504657","https://openalex.org/W400441363","https://openalex.org/W1224261078","https://openalex.org/W1485532853","https://openalex.org/W1491396844","https://openalex.org/W1514205146","https://openalex.org/W1950777589","https://openalex.org/W1973669708","https://openalex.org/W1981276685","https://openalex.org/W1986301630","https://openalex.org/W1994530392","https://openalex.org/W1998229164","https://openalex.org/W1998742693","https://openalex.org/W2002311796","https://openalex.org/W2005522781","https://openalex.org/W2009106392","https://openalex.org/W2014768838","https://openalex.org/W2025905137","https://openalex.org/W2026136559","https://openalex.org/W2042331051","https://openalex.org/W2046907942","https://openalex.org/W2050693797","https://openalex.org/W2065854286","https://openalex.org/W2069976350","https://openalex.org/W2108215203","https://openalex.org/W2109779438","https://openalex.org/W2112748425","https://openalex.org/W2116746197","https://openalex.org/W2117011797","https://openalex.org/W2118446434","https://openalex.org/W2126597753","https://openalex.org/W2128621997","https://openalex.org/W2132054610","https://openalex.org/W2133640977","https://openalex.org/W2142352807","https://openalex.org/W2143908786","https://openalex.org/W2147706354","https://openalex.org/W2148898720","https://openalex.org/W2150678643","https://openalex.org/W2152933780","https://openalex.org/W2164502538","https://openalex.org/W2188162373","https://openalex.org/W2278188939","https://openalex.org/W2296581541","https://openalex.org/W2334833135","https://openalex.org/W2396130155","https://openalex.org/W2405774341","https://openalex.org/W2490695385","https://openalex.org/W2596054757","https://openalex.org/W2915722758","https://openalex.org/W4241395986"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2545131480","https://openalex.org/W2087341511","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,17,167],"feature":[3,15],"enhancement":[4],"method":[5,91],"that":[6],"uses":[7],"neural":[8],"networks":[9],"(NNs)":[10],"to":[11,20,55,129,189,220,240],"map":[12],"the":[13,57,76,83,86,95,110,114,130,190,198,209,221,241],"reverberant":[14,73],"in":[16,166],"log-melspectral":[18],"domain":[19],"its":[21],"corresponding":[22],"anechoic":[23],"feature.":[24],"The":[25,59,89],"mapping":[26],"is":[27],"done":[28],"by":[29,66,100,132,139,151,160,202,223,227,243,247],"cascade":[30],"NNs":[31],"trained":[32],"using":[33,43,67,101,116,133,140,152,200,203,224,244],"Cascade2":[34],"algorithm":[35],"with":[36],"an":[37],"implementation":[38],"of":[39,61,97,123,144,158,173,186,192,206,217,237],"segment-based":[40],"normalization.":[41],"Experiments":[42],"speaker":[44,162],"identification":[45,175],"(SID)":[46],"and":[47,71,105,121,135,179,235,250],"automatic":[48],"speech":[49],"recognition":[50],"(ASR)":[51],"systems":[52,99],"were":[53],"conducted":[54,65],"evaluate":[56],"method.":[58],"experiments":[60],"SID":[62],"system":[63],"was":[64,80,184],"our":[68],"own":[69],"simulated":[70,134,225],"real":[72,136,245],"datasets,":[74],"while":[75],"CENSREC-4":[77],"evaluation":[78,84,115,199],"framework":[79],"used":[81],"as":[82,109,208],"for":[85,146],"ASR":[87],"system.":[88],"proposed":[90],"could":[92,170,214,232],"remarkably":[93],"improve":[94],"performance":[96],"both":[98],"limited":[102],"stereo":[103],"data":[104,108],"low":[106],"speaker-variant":[107],"training":[111,211],"data.":[112],"From":[113,197],"SID,":[117],"we":[118,169,213,231],"reached":[119],"26.0%":[120],"34.8%":[122],"error":[124],"rate":[125,176],"reduction":[126],"(ERR)":[127],"relative":[128,188,219,239],"baseline":[131,222,242],"data,":[137,212],"respectively,":[138],"only":[141],"one":[142,161,251],"pair":[143],"utterances":[145,159,207,226,246],"matched":[147],"condition":[148],"cases.":[149],"Then,":[150],"combined":[153],"dataset":[154],"containing":[155],"15":[156],"pairs":[157,205],"from":[163],"three":[164],"positions":[165],"room,":[168],"reach":[171,215,233],"93.7%":[172],"average":[174],"(three":[177],"known":[178],"two":[180],"unknown":[181],"positions),":[182],"which":[183],"42.2%":[185],"ERR":[187,218,238],"use":[191],"cepstral":[193],"mean":[194],"normalization":[195],"(CMN).":[196],"ASR,":[201],"40":[204],"NN":[210],"78.4%":[216],"five":[228,248],"speakers.":[229],"Moreover,":[230],"75.4%":[234],"71.6%":[236],"speakers":[249],"speaker,":[252],"respectively.":[253]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}