{"id":"https://openalex.org/W4416799671","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249106","title":"Estimating Speaker's Seating Position from Monaural Speech in a Simulated Vehicle Interior Sound Field","display_name":"Estimating Speaker's Seating Position from Monaural Speech in a Simulated Vehicle Interior Sound Field","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799671","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249106"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5109371432","display_name":"Masataka Kaneko","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Kaneko","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38746468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7466999888420105,"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":0.7466999888420105,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.08089999854564667,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.0357000008225441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.9289000034332275},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7315000295639038},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.7027999758720398},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5565000176429749},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.482699990272522},{"id":"https://openalex.org/keywords/sound-power","display_name":"Sound power","score":0.45809999108314514},{"id":"https://openalex.org/keywords/sound-intensity","display_name":"Sound intensity","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9289000034332275},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7315000295639038},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.7063000202178955},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.7027999758720398},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5210999846458435},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.482699990272522},{"id":"https://openalex.org/C67514181","wikidata":"https://www.wikidata.org/wiki/Q1588477","display_name":"Sound power","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C63981117","wikidata":"https://www.wikidata.org/wiki/Q1140289","display_name":"Sound intensity","level":3,"score":0.38499999046325684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32760000228881836},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.3165000081062317},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C104138954","wikidata":"https://www.wikidata.org/wiki/Q5280449","display_name":"Directional sound","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C2780673119","wikidata":"https://www.wikidata.org/wiki/Q487192","display_name":"Muzzle","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1974981856","https://openalex.org/W1982329800","https://openalex.org/W2056951869","https://openalex.org/W2060108923","https://openalex.org/W2094710516","https://openalex.org/W2113638573","https://openalex.org/W2763188033","https://openalex.org/W2794506738","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W3166898278"],"related_works":[],"abstract_inverted_index":{"We":[0],"aim":[1],"to":[2,6,61,85,91,122],"establish":[3],"a":[4,12,19,23,27,35,43,50,70,73,111,115,131,140,209],"method":[5,266],"estimate":[7,62,86,123],"the":[8,31,40,53,63,87,95,98,107,124,127,137,145,151,156,160,167,182,194,198,202,214,217,221,224,243,246,250,258,264,278,287,299],"seating":[9,32,64,152,168,199,227],"position":[10,33,65,153,169,200],"of":[11,34,42,52,97,117,139,144,196,216,223,245,252],"speaker":[13],"from":[14,94,154],"monaural":[15,146,157,203,274],"speech":[16,47,147,158,204],"recorded":[17,48,109],"by":[18,174,205,293],"driving":[20,54],"recorder":[21,55],"in":[22,79,130,181,208],"vehicle.":[24],"There":[25],"is":[26,56,83,103,164,171,267],"demand":[28],"for":[29,269],"identifying":[30],"driver":[36],"and":[37,220,226,233,249,254,262,285,291],"passengers":[38],"after":[39],"occurrence":[41],"traffic":[44],"accident.":[45],"Since":[46],"with":[49,76,110],"microphone":[51,113,225,279],"often":[57],"available,":[58],"we":[59,192],"attempt":[60],"using":[66,185,201,273,294],"those":[67,176],"speeches.":[68],"If":[69],"person":[71],"hears":[72],"sound":[74,88,108,133,211,270],"directly":[75],"their":[77],"ear":[78],"real":[80],"space,":[81],"it":[82,102,120,163],"possible":[84,173],"source":[89,271],"direction":[90],"some":[92],"extent":[93],"characteristics":[96],"pinna,":[99],"even":[100],"if":[101,277],"one":[104],"ear.":[105],"However,":[106],"mono":[112],"has":[114],"loss":[116],"information,":[118],"making":[119],"difficult":[121],"direction.":[125],"On":[126],"other":[128],"hand,":[129],"closed":[132],"field,":[134],"such":[135],"as":[136],"inside":[138],"vehicle,":[141],"acoustic":[142,178],"features":[143],"differ":[148],"depending":[149],"on":[150],"which":[155],"reaches":[159],"microphone.":[161],"Therefore,":[162],"expected":[165],"that":[166,240],"estimation":[170],"still":[172],"modeling":[175],"subtle":[177],"feature":[179],"differences":[180],"individual":[183],"vehicles":[184],"machine":[186],"learning":[187],"techniques.":[188],"In":[189],"this":[190],"paper,":[191],"investigate":[193],"possibility":[195],"estimating":[197],"conducting":[206],"experiments":[207],"simulated":[210],"field":[212],"where":[213],"size":[215,244],"vehicle":[218,247],"interior":[219,248],"arrangement":[222,251],"positions":[228,280],"are":[229,256,281],"consistent":[230],"during":[231,260,283],"training":[232,261,284],"testing.":[234],"The":[235],"experimental":[236],"results":[237],"have":[238],"demonstrated":[239],"1)":[241],"when":[242],"microphones":[253],"seats":[255],"almost":[257],"same":[259],"testing,":[263,286],"proposed":[265],"effective":[268],"localization":[272],"audio,":[275],"2)":[276],"different":[282],"performance":[288,300],"degrades":[289],"significantly,":[290],"3)":[292],"multiple":[295],"utterances":[296],"per":[297],"person,":[298],"can":[301],"be":[302],"further":[303],"improved.":[304]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}