{"id":"https://openalex.org/W3033833751","doi":"https://doi.org/10.1145/3372278.3390730","title":"At the Speed of Sound: Efficient Audio Scene Classification","display_name":"At the Speed of Sound: Efficient Audio Scene Classification","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033833751","doi":"https://doi.org/10.1145/3372278.3390730","mag":"3033833751"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390730","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","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/A5035080566","display_name":"Bo Dong","orcid":"https://orcid.org/0000-0001-7695-9072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bo Dong","raw_affiliation_strings":["NEC Laboratories America & University of Texas at Dallas, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America & University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029827712","display_name":"Cristian Lumezanu","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristian Lumezanu","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645187","display_name":"Yuncong Chen","orcid":"https://orcid.org/0000-0001-5111-3716"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuncong Chen","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013197657","display_name":"Dongjin Song","orcid":"https://orcid.org/0000-0002-7027-7916"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongjin Song","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021325968","display_name":"Takehiko Mizoguchi","orcid":"https://orcid.org/0000-0002-6213-6996"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takehiko Mizoguchi","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456786","display_name":"Haifeng Chen","orcid":"https://orcid.org/0000-0002-9363-738X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haifeng Chen","raw_affiliation_strings":["NEC Laboratories America, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005002693","display_name":"Latifur Khan","orcid":"https://orcid.org/0000-0002-9300-1576"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Latifur Khan","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5035080566"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.7577,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70269914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"301","last_page":"305"},"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9941999912261963,"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":0.8410588502883911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5996369123458862},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5332165956497192},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5198774337768555},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.49909377098083496},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4808426797389984},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4227336347103119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41462868452072144},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1870717704296112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410588502883911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5996369123458862},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5332165956497192},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5198774337768555},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.49909377098083496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4808426797389984},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4227336347103119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41462868452072144},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1870717704296112},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390730","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1524521400","https://openalex.org/W2013824652","https://openalex.org/W2047411082","https://openalex.org/W2052384514","https://openalex.org/W2096733369","https://openalex.org/W2100772705","https://openalex.org/W2171775068","https://openalex.org/W2327143552","https://openalex.org/W2566935005","https://openalex.org/W2626699878","https://openalex.org/W2745969942","https://openalex.org/W2802922942","https://openalex.org/W2807977755","https://openalex.org/W2893538180","https://openalex.org/W2914304175","https://openalex.org/W2917294828","https://openalex.org/W2917819557","https://openalex.org/W2943413028","https://openalex.org/W2963403868","https://openalex.org/W2963500860","https://openalex.org/W2964308564","https://openalex.org/W2972824267","https://openalex.org/W3099206234","https://openalex.org/W4210701857","https://openalex.org/W6662572085"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W3043119899","https://openalex.org/W2766269877"],"abstract_inverted_index":{"Efficient":[0],"audio":[1,38,47,56,73,81],"scene":[2,23,60],"classification":[3,24],"is":[4],"essential":[5],"for":[6,36,89],"smart":[7],"sensing":[8],"platforms":[9],"such":[10],"as":[11],"robots,":[12],"medical":[13],"monitoring,":[14],"surveillance,":[15],"or":[16],"autonomous":[17],"vehicles.":[18],"We":[19,40],"propose":[20],"a":[21,45,59,67,92],"retrieval-based":[22],"architecture":[25],"that":[26,50,62,77],"combines":[27],"recurrent":[28],"neural":[29],"networks":[30],"and":[31,61],"attention":[32],"to":[33],"compute":[34],"embeddings":[35],"short":[37],"segments.":[39],"train":[41],"our":[42],"framework":[43],"using":[44],"custom":[46],"loss":[48],"function":[49],"captures":[51],"both":[52],"the":[53,98,104],"relevance":[54],"of":[55,63,97],"segments":[57],"within":[58,66],"sound":[64],"events":[65],"segment.":[68],"Using":[69],"experiments":[70],"on":[71],"real":[72],"scenes,":[74],"we":[75,78],"show":[76],"can":[79],"discriminate":[80],"scenes":[82],"with":[83],"high":[84],"accuracy":[85,100],"after":[86,102],"listening":[87],"in":[88],"less":[90],"than":[91],"second.":[93],"This":[94],"preserves":[95],"93%":[96],"detection":[99],"obtained":[101],"hearing":[103],"entire":[105],"scene.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}