{"id":"https://openalex.org/W2900030058","doi":"https://doi.org/10.1109/iwaenc.2018.8521410","title":"A Speech Enhancement System for Automotive Speech Recognition with a Hybrid Voice Activity Detection Method","display_name":"A Speech Enhancement System for Automotive Speech Recognition with a Hybrid Voice Activity Detection Method","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900030058","doi":"https://doi.org/10.1109/iwaenc.2018.8521410","mag":"2900030058"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5045610213","display_name":"Haikun Wang","orcid":"https://orcid.org/0000-0002-2565-5543"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haikun Wang","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045610213"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3303,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.57561493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/speech-recognition","display_name":"Speech recognition","score":0.8102158308029175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.776639997959137},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7664207220077515},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7476521134376526},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6743822693824768},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4577944874763489},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.45466795563697815},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43775850534439087},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.43605396151542664},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4266320765018463},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42496025562286377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31322506070137024},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20949620008468628},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07590770721435547}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8102158308029175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776639997959137},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7664207220077515},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7476521134376526},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6743822693824768},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4577944874763489},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.45466795563697815},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43775850534439087},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.43605396151542664},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4266320765018463},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42496025562286377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31322506070137024},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20949620008468628},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07590770721435547},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/iwaenc.2018.8521410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W9455070","https://openalex.org/W79006150","https://openalex.org/W168238592","https://openalex.org/W1493508175","https://openalex.org/W1515932869","https://openalex.org/W1834466884","https://openalex.org/W1891272442","https://openalex.org/W1985242443","https://openalex.org/W2016100027","https://openalex.org/W2038051158","https://openalex.org/W2048497537","https://openalex.org/W2051170812","https://openalex.org/W2061074721","https://openalex.org/W2065296125","https://openalex.org/W2072219999","https://openalex.org/W2075390205","https://openalex.org/W2110622865","https://openalex.org/W2115969105","https://openalex.org/W2126942983","https://openalex.org/W2129012440","https://openalex.org/W2133119590","https://openalex.org/W2140435203","https://openalex.org/W2142170306","https://openalex.org/W2145476772","https://openalex.org/W2146324387","https://openalex.org/W2158146178","https://openalex.org/W2169147844","https://openalex.org/W2172265180","https://openalex.org/W2286130239","https://openalex.org/W2294745040","https://openalex.org/W2406262283","https://openalex.org/W2804690068","https://openalex.org/W3149497261","https://openalex.org/W4249052411","https://openalex.org/W6603237181","https://openalex.org/W6606794619","https://openalex.org/W6629537976","https://openalex.org/W6697247452"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W2131486661"],"abstract_inverted_index":{"This":[0,102],"paper":[1],"presents":[2],"a":[3,99,118],"front-end":[4],"speech":[5,10,37,46,83,95,103,132,166],"enhancement":[6,133],"approach":[7],"to":[8,34,64,74,92,116],"robust":[9],"recognition":[11,167],"in":[12,62,145],"automotive":[13,147],"environments.":[14,148],"It":[15],"combines":[16],"hybrid":[17,119],"voice":[18],"activity":[19],"detection":[20],"(VAD),":[21],"relative":[22],"transfer":[23],"function":[24],"(RT-F)":[25],"based":[26],"generalized":[27],"sidelobe":[28],"cancelation,":[29],"and":[30,84,140,164],"single-channel":[31],"post":[32],"filtering":[33],"enhance":[35],"the":[36,43,59,94,110,124,127,131,153,159],"signal":[38],"of":[39,45,58,112,130,161],"interest,":[40],"thereby":[41],"improving":[42],"robustness":[44],"recognition.":[47],"First,":[48],"we":[49],"choose":[50],"four":[51],"typical":[52],"driving":[53],"scenarios,":[54],"which":[55,121],"include":[56],"most":[57],"noise":[60],"types":[61],"automobiles":[63],"record":[65],"training":[66],"data.":[67],"The":[68,86,149],"recorded":[69],"data":[70],"is":[71,106],"then":[72,107],"used":[73,91],"train":[75],"deep":[76],"neural":[77],"network":[78],"models":[79],"(DNNs)":[80],"for":[81,126],"both":[82,162],"noise.":[85],"trained":[87],"DNNs":[88],"are":[89,143],"subsequently":[90],"estimate":[93],"presence":[96,104],"probability":[97,105],"on":[98],"frame-by-frame":[100],"basis.":[101],"combined":[108],"with":[109],"output":[111],"an":[113],"energy-based":[114],"VAD":[115,163],"form":[117],"VAD,":[120],"serves":[122],"as":[123],"basis":[125],"rest":[128],"components":[129],"system,":[134],"including":[135],"RTF":[136],"estimation,":[137],"adaptive":[138],"beamforming,":[139],"post-filtering.":[141],"Experiments":[142],"conducted":[144],"real":[146],"results":[150],"show":[151],"that":[152],"developed":[154],"method":[155],"can":[156],"significantly":[157],"improve":[158],"performance":[160],"automatic":[165],"(ASR).":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}