{"id":"https://openalex.org/W4372260241","doi":"https://doi.org/10.1109/icassp49357.2023.10097115","title":"SARdBScene: Dataset and Resnet Baseline for Audio Scene Source Counting and Analysis","display_name":"SARdBScene: Dataset and Resnet Baseline for Audio Scene Source Counting and Analysis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260241","doi":"https://doi.org/10.1109/icassp49357.2023.10097115"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097115","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5046605996","display_name":"Michael Nigro","orcid":"https://orcid.org/0000-0002-2343-1714"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Michael Nigro","raw_affiliation_strings":["Toronto Metropolitan University,Dept. of Electrical, Computer, and Biomedical Engineering,Toronto,Ontario,Canada,M5B 2K3"],"affiliations":[{"raw_affiliation_string":"Toronto Metropolitan University,Dept. of Electrical, Computer, and Biomedical Engineering,Toronto,Ontario,Canada,M5B 2K3","institution_ids":["https://openalex.org/I530967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086845888","display_name":"Sridhar Krishnan","orcid":"https://orcid.org/0000-0002-4659-564X"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sridhar Krishnan","raw_affiliation_strings":["Toronto Metropolitan University,Dept. of Electrical, Computer, and Biomedical Engineering,Toronto,Ontario,Canada,M5B 2K3"],"affiliations":[{"raw_affiliation_string":"Toronto Metropolitan University,Dept. of Electrical, Computer, and Biomedical Engineering,Toronto,Ontario,Canada,M5B 2K3","institution_ids":["https://openalex.org/I530967"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046605996"],"corresponding_institution_ids":["https://openalex.org/I530967"],"apc_list":null,"apc_paid":null,"fwci":0.4075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54015649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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/baseline","display_name":"Baseline (sea)","score":0.8024329543113708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7904338240623474},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5642340183258057},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5315734148025513},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5295416116714478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45515957474708557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42795905470848083},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.38189131021499634},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14719516038894653},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.050551146268844604}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8024329543113708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904338240623474},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5642340183258057},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5315734148025513},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5295416116714478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45515957474708557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42795905470848083},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.38189131021499634},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14719516038894653},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.050551146268844604},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097115","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2081074144","https://openalex.org/W2083751884","https://openalex.org/W2088850873","https://openalex.org/W2566935005","https://openalex.org/W2771361008","https://openalex.org/W2775794021","https://openalex.org/W2809072552","https://openalex.org/W2898395910","https://openalex.org/W2952752702","https://openalex.org/W2959539607","https://openalex.org/W2976594877","https://openalex.org/W3004750774","https://openalex.org/W3005501015","https://openalex.org/W3006275583","https://openalex.org/W3015700860","https://openalex.org/W3016244460","https://openalex.org/W3024400986","https://openalex.org/W3033907960","https://openalex.org/W3135871143","https://openalex.org/W3161638288","https://openalex.org/W3176411119","https://openalex.org/W4225939130"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W1975359510","https://openalex.org/W3110605476","https://openalex.org/W1803351015","https://openalex.org/W2363106653"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,16,34,41,46,71],"first":[4],"of":[5,48,57,74,90],"its":[6],"kind":[7],"dataset":[8,43],"for":[9,19,29,95],"audio":[10,20,30,58,79,96],"scene":[11,59],"analysis":[12,80],"(ASA)":[13],"and":[14,39,50,92,103],"presents":[15],"baseline":[17,83],"approach":[18,84],"source":[21,31,97],"counting.":[22],"SARdBScene":[23],"is":[24],"developed":[25],"to":[26,100,107],"promote":[27],"research":[28],"counting,":[32],"as":[33],"relatively":[35],"new":[36],"ASA":[37],"task,":[38],"present":[40],"comprehensive":[42],"that":[44,68],"covers":[45],"variety":[47],"scenarios":[49],"audio-based":[51],"tasks.":[52],"It":[53],"contains":[54],"80":[55],"hours":[56],"mixtures":[60],"depicting":[61],"four":[62],"distinct":[63],"environments":[64],"with":[65],"detailed":[66],"annotations":[67],"make":[69],"it":[70],"unique":[72],"collection":[73],"curated":[75],"data":[76],"in":[77],"the":[78],"landscape.":[81],"Our":[82],"using":[85],"ResNet":[86],"establishes":[87],"state-of-the-art":[88],"results":[89],"77.3%":[91],"85.7%":[93],"accuracy":[94],"counting":[98,105],"up":[99,106],"12":[101],"sources":[102],"speaker":[104],"4":[108],"speakers,":[109],"respectively.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}