{"id":"https://openalex.org/W2289571181","doi":"https://doi.org/10.1109/apsipa.2015.7415485","title":"Speech selection and environmental adaptation for asynchronous speech recognition","display_name":"Speech selection and environmental adaptation for asynchronous speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2289571181","doi":"https://doi.org/10.1109/apsipa.2015.7415485","mag":"2289571181"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5041413561","display_name":"Bo Ren","orcid":"https://orcid.org/0000-0002-0481-5069"},"institutions":[{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]},{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Bo Ren","raw_affiliation_strings":["Nagaoka University of Technology, Nagaoka, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Nagaoka, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Nagaoka University of Technology, Nagaoka, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Nagaoka, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071123569","display_name":"Atsuhiko Kai","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiko Kai","raw_affiliation_strings":["Shizuoka University, Hamamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University, Hamamatsu, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083198820","display_name":"Zhaofeng Zhang","orcid":"https://orcid.org/0000-0003-1797-7507"},"institutions":[{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]},{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhaofeng Zhang","raw_affiliation_strings":["Nagaoka University of Technology, Nagaoka, Japan"],"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Nagaoka, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041413561"],"corresponding_institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"],"apc_list":null,"apc_paid":null,"fwci":0.4484,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7870058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"119","last_page":"124"},"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":0.9993000030517578,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.7986418604850769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893518209457397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.753381073474884},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.685616135597229},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6661373376846313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5321114659309387},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5211125016212463},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.5187295079231262},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48157596588134766},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45571282505989075},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41588425636291504},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41446739435195923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3733154535293579},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11537441611289978},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10939690470695496},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06666639447212219}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7986418604850769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893518209457397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.753381073474884},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.685616135597229},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6661373376846313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5321114659309387},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5211125016212463},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.5187295079231262},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48157596588134766},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45571282505989075},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41588425636291504},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41446739435195923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3733154535293579},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11537441611289978},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10939690470695496},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06666639447212219},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W190289757","https://openalex.org/W232876404","https://openalex.org/W1498436455","https://openalex.org/W1504755800","https://openalex.org/W1524333225","https://openalex.org/W1585276604","https://openalex.org/W1765329493","https://openalex.org/W1973669708","https://openalex.org/W1982846521","https://openalex.org/W1989163463","https://openalex.org/W1989314204","https://openalex.org/W1991234575","https://openalex.org/W1992713442","https://openalex.org/W1993882792","https://openalex.org/W1998229164","https://openalex.org/W2002342963","https://openalex.org/W2012897754","https://openalex.org/W2026369565","https://openalex.org/W2037740282","https://openalex.org/W2047769394","https://openalex.org/W2052117542","https://openalex.org/W2053150333","https://openalex.org/W2069976350","https://openalex.org/W2100495367","https://openalex.org/W2103564015","https://openalex.org/W2106554350","https://openalex.org/W2107992675","https://openalex.org/W2110322414","https://openalex.org/W2114782757","https://openalex.org/W2130640611","https://openalex.org/W2130722890","https://openalex.org/W2132214945","https://openalex.org/W2136922672","https://openalex.org/W2142117481","https://openalex.org/W2144467445","https://openalex.org/W2147768505","https://openalex.org/W2159948109","https://openalex.org/W2160815625","https://openalex.org/W2166772024","https://openalex.org/W2213952365","https://openalex.org/W2219673179","https://openalex.org/W2400691855","https://openalex.org/W2402919203","https://openalex.org/W3176255527","https://openalex.org/W6607679263","https://openalex.org/W6609126827","https://openalex.org/W6631362777","https://openalex.org/W6645850254","https://openalex.org/W6676279616","https://openalex.org/W6689177504"],"related_works":["https://openalex.org/W2545798066","https://openalex.org/W2385145472","https://openalex.org/W2351541234","https://openalex.org/W2504308083","https://openalex.org/W1969439651","https://openalex.org/W2013108665","https://openalex.org/W2738771020","https://openalex.org/W1607021895","https://openalex.org/W2733029664","https://openalex.org/W2801062816"],"abstract_inverted_index":{"In":[0],"this":[1,65],"paper,":[2,66],"we":[3,86],"propose":[4],"a":[5,73,109,117,122],"robust":[6],"distant-talking":[7,53],"speech":[8,13,22,54,100,145],"recognition":[9,55],"system":[10,62,163],"with":[11,31,56,125,142],"asynchronous":[12,21,57,99,144],"recording.":[14],"This":[15],"is":[16],"implemented":[17],"by":[18,67,107,116,128],"combining":[19],"automatic":[20,98,143],"(microphone":[23],"or":[24],"mobile":[25,40,58,131],"terminal)":[26],"selection":[27,146],"and":[28,97,119,147],"environmental":[29,95,148],"adaptation":[30,96],"deep":[32,90],"neural":[33,91],"network":[34,92],"based":[35,138],"framework.":[36],"Although":[37],"applications":[38],"using":[39,68,108,134],"terminals":[41],"have":[42],"attracted":[43],"increasing":[44],"attention,":[45],"there":[46],"are":[47],"few":[48],"studies":[49],"that":[50],"focus":[51],"on":[52],"terminals.":[59,132],"For":[60],"the":[61,80,88,135,150,161,167],"proposed":[63,103],"in":[64,121],"bottleneck":[69,136],"Features":[70],"(BFs)":[71],"from":[72,158],"Deep":[74],"Neural":[75],"Network":[76],"(DNN)":[77],"rather":[78],"than":[79],"conventional":[81],"Mel-Frequency":[82],"Cesptral":[83],"Coefficients":[84],"(MFCCs),":[85],"adopted":[87],"state-of-the-art":[89],"acoustic":[93,140],"model,":[94],"selection.":[101],"The":[102],"method":[104],"was":[105,114,156,172],"evaluated":[106],"reverberant":[110],"WSJCAM0":[111],"corpus,":[112],"which":[113],"emitted":[115],"loudspeaker":[118],"recorded":[120],"meeting":[123],"room":[124],"multiple":[126,130],"speakers":[127],"far-field":[129],"By":[133],"features":[137],"DNN":[139],"model":[141],"adaptation,":[149],"average":[151],"Word":[152],"Error":[153],"Rate":[154],"(WER)":[155],"reduced":[157],"55.32%":[159],"of":[160],"baseline":[162],"to":[164],"19.38%,":[165],"i.e.":[166],"relative":[168],"error":[169],"reduction":[170],"rate":[171],"64.97%.":[173]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}