{"id":"https://openalex.org/W4402474227","doi":"https://doi.org/10.1109/access.2024.3459423","title":"On the Acoustic-Based Recognition of Multiple Objects Using Overlapped Impact Sounds","display_name":"On the Acoustic-Based Recognition of Multiple Objects Using Overlapped Impact Sounds","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402474227","doi":"https://doi.org/10.1109/access.2024.3459423"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3459423","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3459423","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3459423","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010107824","display_name":"Van-Thuan Tran","orcid":"https://orcid.org/0000-0002-3197-679X"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Van-Thuan Tran","raw_affiliation_strings":["Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan","Department of Electronic Engineering, National Taipei University of Technology, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-3197-679X","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]},{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020303183","display_name":"Wei-Ho Tsai","orcid":"https://orcid.org/0000-0002-0867-7951"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Ho Tsai","raw_affiliation_strings":["Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan","Department of Electronic Engineering, National Taipei University of Technology, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0867-7951","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]},{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010107824"],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14026956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"135651","last_page":"135666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9438999891281128,"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"}},"topics":[{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9438999891281128,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9315000176429749,"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/computer-science","display_name":"Computer science","score":0.7064936757087708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5228943228721619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3626982569694519},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3620900511741638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064936757087708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5228943228721619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3626982569694519},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3620900511741638}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3459423","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3459423","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4659feccedaa4b2c83ae5a6ee8943994","is_oa":true,"landing_page_url":"https://doaj.org/article/4659feccedaa4b2c83ae5a6ee8943994","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 135651-135666 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3459423","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3459423","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G5796867822","display_name":null,"funder_award_id":"NSTC 112-2221-E-027-098","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2113897020","https://openalex.org/W2116681922","https://openalex.org/W2150540137","https://openalex.org/W2172073751","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2549219790","https://openalex.org/W2593097720","https://openalex.org/W2735025588","https://openalex.org/W2798421454","https://openalex.org/W2798991696","https://openalex.org/W2888248339","https://openalex.org/W2895085622","https://openalex.org/W2962898576","https://openalex.org/W2963446712","https://openalex.org/W2972418643","https://openalex.org/W3006646738","https://openalex.org/W3018757597","https://openalex.org/W3023352935","https://openalex.org/W3035524453","https://openalex.org/W3083566224","https://openalex.org/W3095715663","https://openalex.org/W4206247269","https://openalex.org/W4281696540","https://openalex.org/W4285117442","https://openalex.org/W4303628775","https://openalex.org/W4312884538","https://openalex.org/W4318776428","https://openalex.org/W4377704392","https://openalex.org/W4385245566","https://openalex.org/W4386076325","https://openalex.org/W4387543539","https://openalex.org/W4389513749","https://openalex.org/W4390638660","https://openalex.org/W4392672392","https://openalex.org/W4400062116","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6776700526","https://openalex.org/W6791762498","https://openalex.org/W6798708526"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0],"a":[1,20,80,126,138,149,239],"recent":[2],"study,":[3],"we":[4,31,78,247],"have":[5],"uncovered":[6],"the":[7,33,49,70,97,102,109,116,129,157,194,202,249,253,267,271,279,284,293,298,304],"potential":[8,203],"of":[9,51,111,115,141,151,182,188,199,238,241,252,281,300],"utilizing":[10],"impact":[11,44,60],"sounds":[12,75],"generated":[13],"when":[14],"objects":[15,38,57,153],"fall":[16,39],"freely":[17],"and":[18,118,123,135,155,167,185,196,215,244,297],"strike":[19],"plane":[21,159],"for":[22,128,204,289],"acoustic-based":[23,63],"object":[24,65,174],"recognition":[25,66,206],"(AOR).":[26],"Building":[27],"upon":[28,225],"this":[29],"discovery,":[30],"address":[32],"practical":[34],"scenario":[35],"where":[36,148],"multiple":[37,56,64],"simultaneously,":[40],"leading":[41],"to":[42,107,218],"overlapped":[43,59,74,168,234],"sounds.":[45],"This":[46,90,162],"investigation":[47],"marks":[48],"inception":[50],"our":[52],"work":[53],"on":[54,137],"recognizing":[55],"using":[58,101],"sounds,":[61],"termed":[62],"(AMOR).":[67],"To":[68],"tackle":[69],"challenges":[71],"posed":[72],"by":[73,270],"in":[76,207,228,292],"AOR,":[77],"propose":[79],"novel":[81],"two-branch":[82],"network":[83,91],"named":[84],"OANet,":[85],"designed":[86],"with":[87,96,232],"overlap":[88,222,294],"awareness.":[89,223],"integrates":[92],"transformer":[93],"encoding":[94],"blocks,":[95],"first":[98,117],"branch":[99],"pre-trained":[100],"supervised":[103,285],"contrastive":[104,286],"learning":[105,287,291],"approach":[106,288],"predict":[108],"number":[110],"objects.":[112],"The":[113],"outputs":[114],"second":[119],"branches":[120],"are":[121],"combined":[122],"fed":[124],"into":[125],"classifier":[127],"AMOR":[130,227],"task.":[131],"We":[132],"conducted":[133],"experiments":[134],"evaluations":[136],"self-collected":[139],"dataset":[140,163],"10":[142,177,245],"distinct":[143],"LEGO":[144],"objects,":[145,179,184,246],"including":[146],"instances":[147],"maximum":[150,240],"three":[152,189],"fell":[154],"hit":[156],"designated":[158],"almost":[160],"concurrently.":[161],"contains":[164],"both":[165],"non-overlapped":[166],"samples":[169,237],"across":[170],"175":[171],"classes":[172],"or":[173],"combinations":[175,181,187],"(i.e.,":[176],"individual":[178],"45":[180],"two":[183],"120":[186],"objects).":[190],"Experimental":[191],"results":[192,268],"underscore":[193],"viability":[195],"promising":[197],"outcomes":[198],"AMOR,":[200],"showcasing":[201],"accurate":[205],"complex":[208,230],"scenarios.":[209],"Notably,":[210],"OANet":[211],"exhibits":[212],"superior":[213],"performance":[214],"robustness":[216],"compared":[217],"baseline":[219,272],"networks":[220],"without":[221],"Furthermore,":[224],"investigating":[226],"more":[229],"scenarios":[231],"mixed":[233,301],"datasets":[235],"containing":[236],"5,":[242],"7,":[243],"observed":[248],"remarkable":[250],"efficiency":[251],"proposed":[254],"OANet.":[255],"It":[256],"consistently":[257],"achieved":[258],"accuracies":[259],"surpassing":[260],"91%,":[261],"which":[262],"were":[263],"14-24%":[264],"higher":[265],"than":[266],"obtained":[269],"models.":[273],"Additionally,":[274],"other":[275],"important":[276],"findings":[277],"include":[278],"effectiveness":[280],"feature":[282,290],"combination,":[283],"detection":[295],"network,":[296],"use":[299],"data":[302],"during":[303],"training":[305],"phase.":[306]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}