{"id":"https://openalex.org/W4413018140","doi":"https://doi.org/10.1109/iv64158.2025.11097719","title":"Fully Convolutional Neural Network-Based Speech Enhancement for In-Vehicle Environment in 3D Perspective","display_name":"Fully Convolutional Neural Network-Based Speech Enhancement for In-Vehicle Environment in 3D Perspective","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4413018140","doi":"https://doi.org/10.1109/iv64158.2025.11097719"},"language":"en","primary_location":{"id":"doi:10.1109/iv64158.2025.11097719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046357357","display_name":"Kaikun Pei","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaikun Pei","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448153","display_name":"Lijun Zhang","orcid":"https://orcid.org/0000-0002-3692-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Zhang","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060792527","display_name":"Dejian Meng","orcid":"https://orcid.org/0000-0003-4153-8109"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejian Meng","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086501723","display_name":"Wei Tian","orcid":"https://orcid.org/0000-0002-5085-7219"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Tian","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632239","display_name":"Zhuang Zhang","orcid":"https://orcid.org/0000-0001-5758-0374"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang Zhang","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062636021","display_name":"Jianfeng Wu","orcid":"https://orcid.org/0000-0002-9243-8936"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Wu","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1222","last_page":"1229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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":0.9958000183105469,"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/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9006999731063843,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7400009632110596},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7374130487442017},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7051810622215271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5721592903137207},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5410685539245605},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46424400806427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29411596059799194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400009632110596},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7374130487442017},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7051810622215271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5721592903137207},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5410685539245605},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46424400806427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29411596059799194},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv64158.2025.11097719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2768245115","display_name":null,"funder_award_id":"62495094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3972003978","display_name":null,"funder_award_id":"CSTB2023NSCQ-MSX0063","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1601700842","https://openalex.org/W1975301756","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2160215673","https://openalex.org/W2291877678","https://openalex.org/W2759814284","https://openalex.org/W2802304149","https://openalex.org/W2889442120","https://openalex.org/W2892110446","https://openalex.org/W2943554574","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2998678989","https://openalex.org/W3012165240","https://openalex.org/W3015844538","https://openalex.org/W3016056257","https://openalex.org/W3016478097","https://openalex.org/W3096408984","https://openalex.org/W3134695619","https://openalex.org/W3147539069","https://openalex.org/W3160085755","https://openalex.org/W3198686072","https://openalex.org/W3207551191","https://openalex.org/W4312550876","https://openalex.org/W4382053577","https://openalex.org/W4392909811","https://openalex.org/W6774779085","https://openalex.org/W6779480587"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2018871932","https://openalex.org/W641279757","https://openalex.org/W370975646","https://openalex.org/W1670566515","https://openalex.org/W4242022592","https://openalex.org/W596972243","https://openalex.org/W2149537132","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Voice":[0],"interaction":[1],"is":[2],"one":[3],"of":[4,9,46,59,62,130,139,215,225],"the":[5,19,42,57,84,101,128,131,140,169,179,187,193,199,203,206,212,222],"important":[6],"development":[7],"directions":[8],"intelligent":[10],"cabins.":[11],"However,":[12],"various":[13],"noise":[14],"interferences":[15],"inside":[16],"and":[17,44,86,122,126,142,151,163,218,228],"outside":[18],"vehicle":[20,66,204],"pose":[21],"significant":[22],"challenges":[23],"to":[24,95],"human-vehicle":[25],"interaction.":[26],"Speech":[27],"enhancement":[28,72,116,171],"technology":[29],"can":[30],"extract":[31],"clear":[32],"speech":[33,37,71,115,170],"signals":[34],"from":[35],"mixed":[36],"signals,":[38],"thereby":[39,166],"significantly":[40,167],"improving":[41],"quality":[43],"intelligibility":[45,61],"voice":[47,63],"commands,":[48],"making":[49],"it":[50],"a":[51,70,92,97,153],"current":[52],"research":[53],"hotspot.":[54],"To":[55],"address":[56],"issue":[58],"low":[60],"commands":[64],"in":[65,91,202,221],"environment,":[67,205],"we":[68,109,146,174],"propose":[69],"method":[73],"based":[74,118],"on":[75,105,119,178,198],"3D":[76,98,123,133,194,207],"tensor":[77,99],"representation.":[78],"Specifically,":[79],"through":[80],"short-time":[81],"Fourier":[82],"transform,":[83],"real":[85],"imaginary":[87],"parts":[88],"are":[89],"concatenated":[90],"new":[93],"dimension":[94],"form":[96],"as":[100],"input":[102],"feature.":[103],"Based":[104],"convolutional":[106],"neural":[107],"networks,":[108],"conducted":[110,175],"systematic":[111],"research,":[112],"building":[113],"UNet":[114],"models":[117],"1D,":[120],"2D,":[121],"convolutions":[124],"respectively,":[125],"compared":[127],"performance":[129],"proposed":[132],"complex":[134,195,208],"domain":[135,155,189,196,209],"model":[136,157,191,197,210],"with":[137],"that":[138,185],"time-domain":[141],"frequency-domain":[143],"models.":[144],"Additionally,":[145],"incorporated":[147],"an":[148],"attention":[149],"mechanism":[150],"developed":[152],"time-frequency":[154,188],"joint":[156,190],"by":[158],"leveraging":[159],"its":[160],"information":[161],"filtering":[162],"focusing":[164],"capabilities,":[165],"enhancing":[168],"effect.":[172],"Finally,":[173],"extensive":[176],"experiments":[177],"Voicebank+Demand":[180],"dataset.":[181],"The":[182],"results":[183],"show":[184],"although":[186],"outperforms":[192],"test":[200],"set,":[201],"achieved":[211],"highest":[213],"scores":[214],"3.67,":[216],"97.94,":[217],"4.36":[219],"respectively":[220],"three":[223],"metrics":[224],"PESQ,":[226],"STOI,":[227],"COVL.":[229]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}