{"id":"https://openalex.org/W2676925568","doi":"https://doi.org/10.1109/icassp.2017.7952131","title":"A comparison of Deep Learning methods for environmental sound detection","display_name":"A comparison of Deep Learning methods for environmental sound detection","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2676925568","doi":"https://doi.org/10.1109/icassp.2017.7952131","mag":"2676925568"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I4210095957","display_name":"Advanced Technologies Application Center","ror":"https://ror.org/00pwma409","country_code":"CU","type":"nonprofit","lineage":["https://openalex.org/I4210095957"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Advanced Technologies Application Center (CENATAV), Habana, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Technologies Application Center (CENATAV), Habana, Cuba","institution_ids":["https://openalex.org/I4210095957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752240","display_name":"Wei Dai","orcid":"https://orcid.org/0000-0003-3543-9606"},"institutions":[{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wei Dai","raw_affiliation_strings":["Inria, Villers-l\u00e8s-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Villers-l\u00e8s-Nancy, France","institution_ids":["https://openalex.org/I4210127166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I4210095957","display_name":"Advanced Technologies Application Center","ror":"https://ror.org/00pwma409","country_code":"CU","type":"nonprofit","lineage":["https://openalex.org/I4210095957"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Advanced Technologies Application Center (CENATAV), Habana, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Technologies Application Center (CENATAV), Habana, Cuba","institution_ids":["https://openalex.org/I4210095957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Stanford University, Stanford, CA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, US","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110454109","display_name":"Samarjit Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samarjit Das","raw_affiliation_strings":["Robert Bosch LLC, Farmington Hills, MI, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC, Farmington Hills, MI, US","institution_ids":["https://openalex.org/I4210120115"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.962,"has_fulltext":false,"cited_by_count":143,"citation_normalized_percentile":{"value":0.98791661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.7443392276763916},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6159312725067139},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5274004340171814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5134063959121704},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5129058361053467},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.512190043926239},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4287665784358978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41573044657707214},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3333872854709625},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17244070768356323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14414942264556885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443392276763916},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6159312725067139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5274004340171814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134063959121704},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5129058361053467},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.512190043926239},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4287665784358978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41573044657707214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3333872854709625},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17244070768356323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14414942264556885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.5699999928474426},{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1511170870","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1650531274","https://openalex.org/W1686810756","https://openalex.org/W1772464306","https://openalex.org/W1836465849","https://openalex.org/W1922655562","https://openalex.org/W1924770834","https://openalex.org/W1980264541","https://openalex.org/W2047918105","https://openalex.org/W2064675550","https://openalex.org/W2085662862","https://openalex.org/W2109606373","https://openalex.org/W2121415728","https://openalex.org/W2143612262","https://openalex.org/W2144012961","https://openalex.org/W2146502635","https://openalex.org/W2384495648","https://openalex.org/W2401869809","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W6631362777","https://openalex.org/W6637940777","https://openalex.org/W6681435938","https://openalex.org/W6713197546"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W4375867731","https://openalex.org/W2909888262","https://openalex.org/W2611989081","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395"],"abstract_inverted_index":{"Environmental":[0],"sound":[1],"detection":[2],"is":[3,26],"a":[4,33],"challenging":[5],"application":[6],"of":[7,11,15,22,35,49,64,88,97],"machine":[8],"learning":[9],"because":[10],"the":[12,16,19,42,98],"noisy":[13],"nature":[14],"signal,":[17],"and":[18,47,52,58,68],"small":[20],"amount":[21],"(labeled)":[23],"data":[24],"that":[25],"typically":[27],"available.":[28,101],"This":[29],"work":[30],"thus":[31],"presents":[32],"comparison":[34],"several":[36],"state-of-the-art":[37],"Deep":[38],"Learning":[39],"models":[40],"on":[41,45],"IEEE":[43],"challenge":[44,56],"Detection":[46],"Classification":[48],"Acoustic":[50],"Scenes":[51],"Events":[53],"(DCASE)":[54],"2016":[55],"task":[57],"data,":[59],"classifying":[60],"sounds":[61],"into":[62],"one":[63,96],"fifteen":[65],"common":[66],"indoor":[67],"outdoor":[69],"acoustic":[70],"scenes,":[71],"such":[72],"as":[73],"bus,":[74],"cafe,":[75],"car,":[76],"city":[77],"center,":[78],"forest":[79],"path,":[80],"library,":[81],"train,":[82],"etc.":[83],"In":[84],"total,":[85],"13":[86],"hours":[87],"stereo":[89],"audio":[90],"recordings":[91],"are":[92],"available,":[93],"making":[94],"this":[95],"largest":[99],"datasets":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
