{"id":"https://openalex.org/W4406858852","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848662","title":"Experimental Evaluation of Speech Enhancement for In-Car Environment Using Blind Source Separation and DNN-based Noise Suppression","display_name":"Experimental Evaluation of Speech Enhancement for In-Car Environment Using Blind Source Separation and DNN-based Noise Suppression","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858852","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848662"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Yutsuki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutsuki Takeuchi","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040475714","display_name":"Taishi Nakashima","orcid":"https://orcid.org/0000-0001-5417-1428"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taishi Nakashima","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116046406","display_name":"Takashi Takazawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Takazawa","raw_affiliation_strings":["MIRISE Technologies,Aichi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIRISE Technologies,Aichi,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116046407","display_name":"Shuhei Shimanoe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhei Shimanoe","raw_affiliation_strings":["MIRISE Technologies,Aichi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIRISE Technologies,Aichi,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102767607","display_name":"Y. Tsuchiya","orcid":"https://orcid.org/0000-0002-6481-8480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshinori Tsuchiya","raw_affiliation_strings":["MIRISE Technologies,Aichi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIRISE Technologies,Aichi,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9871000051498413,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9678000211715698,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7381641268730164},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.713468074798584},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6374375224113464},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6070120334625244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6008671522140503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5858159065246582},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5845252275466919},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.49320071935653687},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4662294387817383},{"id":"https://openalex.org/keywords/noise-suppression","display_name":"Noise suppression","score":0.41423526406288147},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.40133145451545715},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2619081139564514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23531663417816162},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12620404362678528},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12436017394065857},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07380512356758118}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7381641268730164},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.713468074798584},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6374375224113464},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6070120334625244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6008671522140503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5858159065246582},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5845252275466919},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.49320071935653687},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4662294387817383},{"id":"https://openalex.org/C2987345804","wikidata":"https://www.wikidata.org/wiki/Q583234","display_name":"Noise suppression","level":3,"score":0.41423526406288147},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.40133145451545715},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2619081139564514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23531663417816162},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12620404362678528},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12436017394065857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07380512356758118},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","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},{"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/apsipaasc63619.2025.10848662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1536252645","https://openalex.org/W1543386260","https://openalex.org/W1544785557","https://openalex.org/W1845880232","https://openalex.org/W2014857913","https://openalex.org/W2019426094","https://openalex.org/W2053165762","https://openalex.org/W2072548008","https://openalex.org/W2099741732","https://openalex.org/W2127851351","https://openalex.org/W2408744528","https://openalex.org/W2610428556","https://openalex.org/W2702006285","https://openalex.org/W2883769586","https://openalex.org/W2889243386","https://openalex.org/W2900030058","https://openalex.org/W2952218014","https://openalex.org/W2977008706","https://openalex.org/W3016244615","https://openalex.org/W3163605974","https://openalex.org/W4375869228","https://openalex.org/W6637245088","https://openalex.org/W6790608195"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,74],"evaluate":[4],"speech":[5,33,106,123,150],"enhancement":[6,53],"using":[7,79],"multi-channel":[8],"blind":[9,23,55],"source":[10,24,56],"separation":[11,25],"(BSS)":[12],"and":[13,34,37,98,100,131,146],"single-channel":[14,60],"DNN-based":[15],"noise":[16,95],"suppression":[17],"in":[18,153],"an":[19],"in-car":[20,154],"environment.":[21],"Specifically,":[22],"is":[26,42],"applied":[27],"to":[28,129,136,148],"a":[29],"mixture":[30],"of":[31,39,66,143],"target":[32],"driving":[35,84],"noise,":[36],"one":[38],"the":[40,45,59,67,76,80,114,121,141],"outputs":[41],"fed":[43],"into":[44],"DNN.":[46],"This":[47],"combination":[48],"allows":[49],"for":[50,94,105,113],"speaker":[51],"position-independent":[52],"through":[54],"separation,":[57],"while":[58],"DNN":[61,147],"can":[62],"be":[63],"trained":[64],"regardless":[65],"microphone":[68],"position.":[69],"To":[70],"further":[71],"improve":[72],"performance,":[73,97],"fine-tune":[75],"pre-trained":[77],"model":[78],"BSS":[81,145],"outputs,":[82],"including":[83],"noise.":[85],"Our":[86],"evaluation":[87],"criteria":[88],"include":[89],"signal-to-distortion":[90],"ratio":[91],"improvement":[92],"(SDRi)":[93],"reduction":[96],"accuracy":[99,125],"character":[101],"error":[102],"rate":[103],"(CER)":[104],"recognition":[107,124,151],"performance.":[108],"Results":[109],"demonstrate":[110,140],"that":[111],"SDRi":[112],"proposed":[115],"method":[116],"reached":[117],"28.37":[118],"dB.":[119],"Additionally,":[120],"average":[122],"improved":[126,133],"from":[127,134],"0.785":[128],"0.826,":[130],"CER":[132],"15.3%":[135],"11.9%.":[137],"These":[138],"findings":[139],"potential":[142],"combining":[144],"enhance":[149],"capabilities":[152],"environments.":[155]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}