{"id":"https://openalex.org/W2095147901","doi":"https://doi.org/10.1109/taslp.2014.2375575","title":"Histogram of gradients of Time-Frequency Representations for Audio Scene Detection","display_name":"Histogram of gradients of Time-Frequency Representations for Audio Scene Detection","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2095147901","doi":"https://doi.org/10.1109/taslp.2014.2375575","mag":"2095147901"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2375575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2375575","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1508.04909","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031137438","display_name":"Alain Rakotomamonjy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alain Rakotomamonjy","raw_affiliation_strings":["LITIS EA 4108, Universit\u00e9 de Rouen, France","LITIS, Universit\u00e9de Rouen, Saint Etienne du Rouvray, France"],"affiliations":[{"raw_affiliation_string":"LITIS EA 4108, Universit\u00e9 de Rouen, France","institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"]},{"raw_affiliation_string":"LITIS, Universit\u00e9de Rouen, Saint Etienne du Rouvray, France","institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003774172","display_name":"Gilles Gasso","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I88814501","display_name":"Institut National des Sciences Appliqu\u00e9es Rouen Normandie","ror":"https://ror.org/020ws7586","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I88814501"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gilles Gasso","raw_affiliation_strings":["LITIS EA 4108, INSA de Rouen, France","LITIS, INSA de Rouen, Saint-\u00c9tienne-du-Rouvray, France"],"affiliations":[{"raw_affiliation_string":"LITIS EA 4108, INSA de Rouen, France","institution_ids":["https://openalex.org/I88814501","https://openalex.org/I4210108118"]},{"raw_affiliation_string":"LITIS, INSA de Rouen, Saint-\u00c9tienne-du-Rouvray, France","institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I88814501"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031137438"],"corresponding_institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"],"apc_list":null,"apc_paid":null,"fwci":14.1231,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99310109,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9961000084877014,"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/histogram","display_name":"Histogram","score":0.8344824910163879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.652321457862854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6249200701713562},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6006816625595093},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5699190497398376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5627280473709106},{"id":"https://openalex.org/keywords/histogram-of-oriented-gradients","display_name":"Histogram of oriented gradients","score":0.5307799577713013},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5014162063598633},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.49826908111572266},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4395413100719452},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4281507432460785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4107673764228821},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.353689968585968},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2090117335319519},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.0712747871875763}],"concepts":[{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8344824910163879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652321457862854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6249200701713562},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6006816625595093},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5699190497398376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627280473709106},{"id":"https://openalex.org/C17426736","wikidata":"https://www.wikidata.org/wiki/Q419918","display_name":"Histogram of oriented gradients","level":4,"score":0.5307799577713013},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5014162063598633},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.49826908111572266},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4395413100719452},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4281507432460785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4107673764228821},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.353689968585968},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2090117335319519},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0712747871875763},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2014.2375575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2375575","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1508.04909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04909","pdf_url":"https://arxiv.org/pdf/1508.04909","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00951990v6","is_oa":true,"landing_page_url":"https://hal.science/hal-00951990","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2015, 23 (1), pp.142-153. &#x27E8;10.1109/TASLP.2014.2375575&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1508.04909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.04909","pdf_url":"https://arxiv.org/pdf/1508.04909","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W34415881","https://openalex.org/W1966976522","https://openalex.org/W1971645240","https://openalex.org/W1996160964","https://openalex.org/W2001297828","https://openalex.org/W2005122913","https://openalex.org/W2006546815","https://openalex.org/W2007885413","https://openalex.org/W2008415856","https://openalex.org/W2020733616","https://openalex.org/W2029409452","https://openalex.org/W2048174296","https://openalex.org/W2066148499","https://openalex.org/W2066941820","https://openalex.org/W2076608692","https://openalex.org/W2102381657","https://openalex.org/W2105622288","https://openalex.org/W2130640900","https://openalex.org/W2139689188","https://openalex.org/W2151103935","https://openalex.org/W2157498370","https://openalex.org/W2161969291","https://openalex.org/W2168356304","https://openalex.org/W2187846082","https://openalex.org/W2405419740","https://openalex.org/W2561557072","https://openalex.org/W4233392025","https://openalex.org/W6675803605","https://openalex.org/W6714052166"],"related_works":["https://openalex.org/W2562641072","https://openalex.org/W2071599417","https://openalex.org/W2048716406","https://openalex.org/W1870444468","https://openalex.org/W1964725559","https://openalex.org/W3109748140","https://openalex.org/W2045053268","https://openalex.org/W2433492094","https://openalex.org/W2767833206","https://openalex.org/W1556327589"],"abstract_inverted_index":{"Presents":[0],"our":[1],"entry":[2],"to":[3,56],"the":[4,24],"Detection":[5],"and":[6,31,39],"Classification":[7],"of":[8,41,50],"Acoustic":[9],"Scenes":[10],"challenge.":[11],"The":[12],"approach":[13],"we":[14],"propose":[15],"for":[16],"classifying":[17],"acoustic":[18],"scenes":[19],"is":[20],"based":[21,47],"on":[22,48],"transforming":[23],"audio":[25],"signal":[26],"into":[27],"a":[28,57],"time-frequency":[29,42],"representation":[30],"then":[32],"in":[33],"extracting":[34],"relevant":[35],"features":[36,45],"about":[37],"shapes":[38],"evolutions":[40],"structures.":[43],"These":[44],"are":[46,53],"histogram":[49],"gradients":[51],"that":[52],"subsequently":[54],"fed":[55],"multi-class":[58],"linear":[59],"support":[60],"vector":[61],"machines.":[62]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
