{"id":"https://openalex.org/W2921922265","doi":"https://doi.org/10.23919/apsipa.2018.8659450","title":"Bottleneck feature-mediated DNN-based feature mapping for throat microphone speech recognition","display_name":"Bottleneck feature-mediated DNN-based feature mapping for throat microphone speech recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921922265","doi":"https://doi.org/10.23919/apsipa.2018.8659450","mag":"2921922265"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659450","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5072119403","display_name":"T. Suzuki","orcid":"https://orcid.org/0000-0002-2314-001X"},"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":true,"raw_author_name":"Takahito Suzuki","raw_affiliation_strings":["Shizuoka University, Shizuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University, Shizuoka, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006504365","display_name":"Jun Ogata","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Ogata","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020888824","display_name":"Takashi Tsunakawa","orcid":"https://orcid.org/0000-0002-3880-6099"},"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":"Takashi Tsunakawa","raw_affiliation_strings":["Shizuoka University, Shizuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University, Shizuoka, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109009818","display_name":"Masafumi Nishida","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":"Masafumi Nishida","raw_affiliation_strings":["Shizuoka University, Shizuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University, Shizuoka, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083574298","display_name":"Masafumi Nishimura","orcid":"https://orcid.org/0000-0001-7633-9340"},"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":"Masafumi Nishimura","raw_affiliation_strings":["Shizuoka University, Shizuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University, Shizuoka, Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072119403"],"corresponding_institution_ids":["https://openalex.org/I1298590031"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69797711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1738","last_page":"1741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9945999979972839,"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/microphone","display_name":"Microphone","score":0.7902498841285706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7777435779571533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636938095092773},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6128841042518616},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.564018726348877},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5028249621391296},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49315375089645386},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4613741636276245},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4416986405849457},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42969435453414917},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42377936840057373},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4157645106315613},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40685439109802246},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4030316472053528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37520018219947815},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08085289597511292},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06742969155311584}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7902498841285706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7777435779571533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636938095092773},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6128841042518616},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.564018726348877},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5028249621391296},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49315375089645386},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4613741636276245},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4416986405849457},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42969435453414917},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42377936840057373},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4157645106315613},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40685439109802246},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4030316472053528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37520018219947815},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08085289597511292},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06742969155311584},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659450","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"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":12,"referenced_works":["https://openalex.org/W1489048302","https://openalex.org/W1524333225","https://openalex.org/W1661756259","https://openalex.org/W2054055524","https://openalex.org/W2141489634","https://openalex.org/W2162449135","https://openalex.org/W2399016933","https://openalex.org/W2786825824","https://openalex.org/W2963266252","https://openalex.org/W6631362777","https://openalex.org/W6683815549","https://openalex.org/W6712686019"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2104528589","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4250904811","https://openalex.org/W2155047054","https://openalex.org/W2379120504"],"abstract_inverted_index":{"Throat":[0,29],"microphones":[1,11,15,82],"are":[2,44],"more":[3],"robust":[4],"to":[5,97,102],"environmental":[6],"noises":[7],"than":[8,25,133],"usual":[9],"acoustic":[10,42,51,81,87,93,141],"such":[12],"as":[13],"close-talk":[14],"because":[16,40],"they":[17],"detect":[18],"speech":[19,37,69,111],"signals":[20],"through":[21],"skin":[22],"vibrations":[23],"rather":[24],"by":[26,80],"air":[27],"transmission.":[28],"microphones,":[30,94],"however,":[31],"cannot":[32],"be":[33],"used":[34],"in":[35],"conventional":[36],"recognition":[38,112],"systems":[39],"their":[41],"characteristics":[43],"much":[45],"different":[46],"from":[47,139],"those":[48],"of":[49,76,114],"the":[50,86,90,99,120,134,140],"microphones.":[52],"In":[53],"this":[54],"study,":[55],"we":[56,95],"propose":[57],"a":[58,73,109,124],"deep":[59],"neural":[60],"network":[61],"(DNN)-based":[62],"feature":[63],"mapping":[64],"method":[65],"for":[66,108],"throat":[67,91],"microphone":[68,142],"recognition.":[70],"To":[71],"utilize":[72],"large":[74],"amount":[75],"training":[77],"data":[78],"recorded":[79],"and":[83,92],"effectively":[84],"reduce":[85],"mismatch":[88],"between":[89,104],"tried":[96],"use":[98],"bottleneck":[100],"features":[101],"mediate":[103],"them.":[105],"Evaluation":[106],"results":[107],"large-vocabulary":[110],"task":[113],"Japanese":[115],"free":[116],"conversation":[117],"revealed":[118],"that":[119],"proposed":[121],"system":[122,137],"had":[123],"45.8%":[125],"lower":[126],"character":[127],"error":[128],"rate":[129],"(75.5%":[130],"\u2192":[131],"40.9%)":[132],"typical":[135],"MFCC":[136],"trained":[138],"data.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}