{"id":"https://openalex.org/W3015272104","doi":"https://doi.org/10.1109/tce.2020.2986003","title":"Speech Enhancement Parameter Adjustment to Maximize Accuracy of Automatic Speech Recognition","display_name":"Speech Enhancement Parameter Adjustment to Maximize Accuracy of Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-04-08","ids":{"openalex":"https://openalex.org/W3015272104","doi":"https://doi.org/10.1109/tce.2020.2986003","mag":"3015272104"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2020.2986003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2020.2986003","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-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/A5002983657","display_name":"Tomoko Kawase","orcid":"https://orcid.org/0000-0002-0670-3319"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoko Kawase","raw_affiliation_strings":["Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0670-3319","affiliations":[{"raw_affiliation_string":"Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101532289","display_name":"Manabu Okamoto","orcid":"https://orcid.org/0009-0004-3612-9639"},"institutions":[{"id":"https://openalex.org/I181097317","display_name":"Sojo University","ror":"https://ror.org/014fz7968","country_code":"JP","type":"education","lineage":["https://openalex.org/I181097317"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Manabu Okamoto","raw_affiliation_strings":["Department of Computer and Information Sciences, Sojo University, Kumamoto, Japan","Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Sojo University, Kumamoto, Japan","institution_ids":["https://openalex.org/I181097317"]},{"raw_affiliation_string":"Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067107593","display_name":"Takaaki Fukutomi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Fukutomi","raw_affiliation_strings":["Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016506002","display_name":"Yamato Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamato Takahashi","raw_affiliation_strings":["Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Intelligence Laboratories, NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8664,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96054005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"66","issue":"2","first_page":"125","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7213772535324097},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.675993800163269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6565391421318054},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5902857184410095},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5852500200271606},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5617696642875671},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5528150796890259},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.48302969336509705},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46223244071006775},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45272424817085266},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44167840480804443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3673303723335266},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27750837802886963},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.14546793699264526},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09628862142562866},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09127667546272278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213772535324097},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.675993800163269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6565391421318054},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5902857184410095},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5852500200271606},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5617696642875671},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5528150796890259},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.48302969336509705},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46223244071006775},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45272424817085266},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44167840480804443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3673303723335266},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27750837802886963},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.14546793699264526},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09628862142562866},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09127667546272278},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2020.2986003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2020.2986003","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1506558619","https://openalex.org/W1556978752","https://openalex.org/W1563939609","https://openalex.org/W1565902586","https://openalex.org/W1659842140","https://openalex.org/W1965739709","https://openalex.org/W1992022774","https://openalex.org/W2005981242","https://openalex.org/W2020405477","https://openalex.org/W2028209924","https://openalex.org/W2054333906","https://openalex.org/W2056332515","https://openalex.org/W2066460453","https://openalex.org/W2081721156","https://openalex.org/W2102607054","https://openalex.org/W2104604339","https://openalex.org/W2122410182","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2134389297","https://openalex.org/W2139229273","https://openalex.org/W2139737683","https://openalex.org/W2145939969","https://openalex.org/W2158336491","https://openalex.org/W2160815625","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2394967684","https://openalex.org/W2487907653","https://openalex.org/W2495589006","https://openalex.org/W2507109542","https://openalex.org/W2533784503","https://openalex.org/W2600379459","https://openalex.org/W2602348424","https://openalex.org/W2609384258","https://openalex.org/W2623293810","https://openalex.org/W2735006420","https://openalex.org/W2752143737","https://openalex.org/W2767005120","https://openalex.org/W2795237500","https://openalex.org/W2805233667","https://openalex.org/W2889243386","https://openalex.org/W2899829828","https://openalex.org/W2921380599","https://openalex.org/W3103619082","https://openalex.org/W4212899374","https://openalex.org/W4249052411","https://openalex.org/W4390861721","https://openalex.org/W6633586552","https://openalex.org/W6633902517"],"related_works":["https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2120771489","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W3008816511","https://openalex.org/W4386746628","https://openalex.org/W2051376034","https://openalex.org/W3036714475","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Consumer":[0],"electronics":[1,111],"equipped":[2],"with":[3,26,112],"a":[4,81,89,169],"microphone":[5],"array,":[6],"such":[7],"as":[8],"car":[9],"navigation":[10],"devices":[11],"and":[12,40,73],"headsets":[13],"commonly":[14],"implement":[15],"speech":[16,52,61,98,132,146],"enhancement":[17,62,133],"techniques":[18,32],"based":[19,153],"on":[20,154],"the":[21,43,59,86,96,109,130,151],"gradient":[22],"method":[23,102,164],"to":[24,70,105,125,144],"cope":[25],"additive":[27],"noise.":[28],"However,":[29],"while":[30],"these":[31],"had":[33],"been":[34,65],"originally":[35],"developed":[36,80],"for":[37,84,134],"voice":[38],"communication":[39],"can":[41,140],"maximize":[42,50],"signal-to-distortion":[44],"ratio":[45],"(SDR),":[46],"they":[47],"cannot":[48],"always":[49],"automatic":[51],"recognition":[53],"(ASR)":[54],"accuracy.":[55],"For":[56],"this":[57,77],"reason,":[58],"front-end":[60,97,131],"parameters":[63],"have":[64],"adjusted":[66,167],"by":[67,93,148,162,168],"human":[68,170],"experts":[69],"each":[71],"environment":[72],"acoustic":[74],"model.":[75],"In":[76,157],"study,":[78],"we":[79],"novel":[82],"system":[83],"maximizing":[85],"accuracy":[87],"of":[88,129],"given":[90],"ASR":[91,107],"engine":[92],"automatically":[94],"adjusting":[95],"enhancement.":[99],"The":[100,137],"proposed":[101],"allows":[103],"consumers":[104],"use":[106],"through":[108],"consumer":[110],"less":[113],"stress":[114],"when":[115],"ambient":[116],"noise":[117,155],"varies.":[118],"A":[119],"genetic":[120],"algorithm":[121],"(GA)":[122],"is":[123],"used":[124],"generate":[126],"parameter":[127,159],"values":[128,139,160],"particular":[135],"environments.":[136],"generated":[138],"be":[141],"dynamically":[142],"assigned":[143],"input":[145],"signals":[147],"preliminarily":[149],"clustering":[150],"environments":[152],"features.":[156],"evaluations,":[158],"determined":[161],"our":[163],"outperformed":[165],"one":[166],"expert.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}