{"id":"https://openalex.org/W2586665961","doi":"https://doi.org/10.1109/slt.2016.7846242","title":"Deep bottleneck features and sound-dependent i-vectors for simultaneous recognition of speech and environmental sounds","display_name":"Deep bottleneck features and sound-dependent i-vectors for simultaneous recognition of speech and environmental sounds","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2586665961","doi":"https://doi.org/10.1109/slt.2016.7846242","mag":"2586665961"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035916201","display_name":"Seiji Kawanishi","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiji Kawanishi","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880946","display_name":"Koichiro Yoshino","orcid":"https://orcid.org/0000-0001-6579-361X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichiro Yoshino","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040108974"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74169346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"35","last_page":"42"},"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/T11309","display_name":"Music 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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928283214569092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7509883046150208},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6785922050476074},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6345415115356445},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6217977404594421},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.6066524982452393},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4688732922077179},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.46422573924064636},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44040462374687195},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4259325861930847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40381020307540894},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4007502794265747},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.23053735494613647},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06400838494300842},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06116896867752075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928283214569092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7509883046150208},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6785922050476074},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6345415115356445},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6217977404594421},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.6066524982452393},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4688732922077179},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.46422573924064636},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44040462374687195},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4259325861930847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40381020307540894},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4007502794265747},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.23053735494613647},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06400838494300842},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06116896867752075},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2016.7846242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W204053250","https://openalex.org/W1499332833","https://openalex.org/W1501987291","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1599512239","https://openalex.org/W1620791691","https://openalex.org/W1631260214","https://openalex.org/W1650531274","https://openalex.org/W1661756259","https://openalex.org/W1978660892","https://openalex.org/W1985090574","https://openalex.org/W1985371235","https://openalex.org/W1989314204","https://openalex.org/W1991139021","https://openalex.org/W2002342963","https://openalex.org/W2012897754","https://openalex.org/W2016882596","https://openalex.org/W2025198378","https://openalex.org/W2044893557","https://openalex.org/W2046972719","https://openalex.org/W2051057783","https://openalex.org/W2070707809","https://openalex.org/W2079623482","https://openalex.org/W2090200552","https://openalex.org/W2094035326","https://openalex.org/W2106554350","https://openalex.org/W2121415728","https://openalex.org/W2121973264","https://openalex.org/W2122178311","https://openalex.org/W2124629003","https://openalex.org/W2133735870","https://openalex.org/W2137630452","https://openalex.org/W2150769028","https://openalex.org/W2165712214","https://openalex.org/W2186582651","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2296483664","https://openalex.org/W2395043307","https://openalex.org/W2405774341","https://openalex.org/W4252049220","https://openalex.org/W4302557958","https://openalex.org/W6601563604","https://openalex.org/W6608353291","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6636898527","https://openalex.org/W6636969168","https://openalex.org/W6644703941","https://openalex.org/W6653316155","https://openalex.org/W6680394064","https://openalex.org/W6682600690","https://openalex.org/W6697003656","https://openalex.org/W6712113799","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2748922771"],"abstract_inverted_index":{"In":[0],"speech":[1,34,41,99,117,156],"interfaces,":[2],"it":[3],"is":[4,17],"often":[5],"necessary":[6],"to":[7,55,91,115,160,197],"understand":[8],"the":[9,25,30,60,93,106,124,184,191],"overall":[10],"auditory":[11],"environment,":[12],"not":[13],"only":[14],"recognizing":[15,40],"what":[16],"being":[18,22],"said,":[19],"but":[20],"also":[21],"aware":[23],"of":[24,76,95,98,108,126,154,193,200],"location":[26],"or":[27],"actions":[28],"surrounding":[29],"utterance.":[31],"However,":[32,148],"automatic":[33],"recognition":[35,97,159,202],"(ASR)":[36],"becomes":[37],"difficult":[38],"when":[39],"with":[42],"environmental":[43,48,66,71,101,119,158],"sounds.":[44,102],"Standard":[45],"solutions":[46],"treat":[47],"sounds":[49,67,72,120],"as":[50,190],"noise,":[51],"and":[52,100,118,122,143,157,173,188],"remove":[53],"them":[54],"improve":[56,123,198],"ASR":[57],"performance.":[58],"On":[59],"other":[61],"hand,":[62],"most":[63],"studies":[64],"on":[65],"construct":[68],"classifiers":[69],"for":[70],"only,":[73],"without":[74],"interference":[75],"spoken":[77],"utterances.":[78],"But,":[79],"in":[80],"reality,":[81],"such":[82],"separate":[83],"situations":[84],"almost":[85],"never":[86],"exist.":[87],"This":[88],"study":[89],"attempts":[90],"address":[92],"problem":[94],"simultaneous":[96,155],"Particularly,":[103],"we":[104,134,149,164],"examine":[105],"possibility":[107],"using":[109],"deep":[110],"neural":[111],"network":[112],"(DNN)":[113],"techniques":[114],"recognize":[116],"simultaneously,":[121],"accuracy":[125,199],"both":[127],"tasks":[128],"under":[129],"respective":[130],"noisy":[131],"conditions.":[132],"First,":[133],"investigate":[135],"DNN":[136],"architectures":[137],"including":[138],"two":[139],"parallel":[140],"single-task":[141],"DNNs,":[142],"a":[144,167],"single":[145],"multi-task":[146,152],"DNN.":[147],"found":[150],"direct":[151],"learning":[153],"be":[161],"difficult.":[162],"Therefore,":[163],"further":[165],"propose":[166],"method":[168],"that":[169,183],"combines":[170],"bottleneck":[171,186],"features":[172,187],"sound-dependent":[174],"i-vectors":[175,189],"within":[176],"this":[177],"framework.":[178],"Experimental":[179],"evaluation":[180],"results":[181],"reveal":[182],"utilizing":[185],"input":[192],"DNNs":[194],"can":[195],"help":[196],"each":[201],"task.":[203]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}