{"id":"https://openalex.org/W2139689188","doi":"https://doi.org/10.1109/icassp.2009.4959924","title":"Audio classification from time-frequency texture","display_name":"Audio classification from time-frequency texture","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2139689188","doi":"https://doi.org/10.1109/icassp.2009.4959924","mag":"2139689188"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/74538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065040470","display_name":"Guoshen Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Guoshen Yu","raw_affiliation_strings":["CMAP, Ecole Polytechinque, Palaiseau, France","CMAP, \u00c9cole Polytechnique 91128 Palaiseau Cedex, France"],"affiliations":[{"raw_affiliation_string":"CMAP, Ecole Polytechinque, Palaiseau, France","institution_ids":["https://openalex.org/I142476485"]},{"raw_affiliation_string":"CMAP, \u00c9cole Polytechnique 91128 Palaiseau Cedex, France","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044026747","display_name":"Jean-Jacques Slotine","orcid":"https://orcid.org/0000-0002-7161-7812"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Jacques Slotine","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","NSL, Massachusetts Institute of Technology, Cambridge, 02139, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"NSL, Massachusetts Institute of Technology, Cambridge, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065040470"],"corresponding_institution_ids":["https://openalex.org/I142476485"],"apc_list":null,"apc_paid":null,"fwci":5.3565,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.95994695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"45","issue":null,"first_page":"1677","last_page":"1680"},"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":0.998199999332428,"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":0.9937999844551086,"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/spectrogram","display_name":"Spectrogram","score":0.8687491416931152},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.72385174036026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023721933364868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6305267214775085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5853222012519836},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5543679594993591},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5510575771331787},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.5189194679260254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4644380211830139},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.45479515194892883},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42269080877304077},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4123566150665283},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3788457214832306},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.272169828414917},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.16251757740974426},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12339234352111816},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.06510329246520996}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8687491416931152},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.72385174036026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023721933364868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305267214775085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5853222012519836},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5543679594993591},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5510575771331787},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.5189194679260254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4644380211830139},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.45479515194892883},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42269080877304077},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4123566150665283},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3788457214832306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.272169828414917},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.16251757740974426},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12339234352111816},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.06510329246520996},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2009.4959924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.250.9742","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.250.9742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/0809.4501v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.559.74","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.559.74","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cmap.polytechnique.fr/~yu/publications/ICASSP09_audio_final.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/74538","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/74538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/74538","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/74538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W34562744","https://openalex.org/W97067864","https://openalex.org/W200160492","https://openalex.org/W1530838232","https://openalex.org/W1565658805","https://openalex.org/W1964538581","https://openalex.org/W2028133852","https://openalex.org/W2043843997","https://openalex.org/W2074188409","https://openalex.org/W2094058414","https://openalex.org/W2115388399","https://openalex.org/W2115755118","https://openalex.org/W2144982973","https://openalex.org/W2158452612","https://openalex.org/W2158477298","https://openalex.org/W2166693890","https://openalex.org/W2168441989","https://openalex.org/W2341514930","https://openalex.org/W2745818372","https://openalex.org/W2949597598","https://openalex.org/W4256399001","https://openalex.org/W6608239544","https://openalex.org/W6634086901","https://openalex.org/W6683396588"],"related_works":["https://openalex.org/W1889291648","https://openalex.org/W2533590149","https://openalex.org/W335396218","https://openalex.org/W1504214173","https://openalex.org/W1600447354","https://openalex.org/W1589126043","https://openalex.org/W2035480840","https://openalex.org/W2602361891","https://openalex.org/W2149263408","https://openalex.org/W2107964963"],"abstract_inverted_index":{"Time-frequency":[0],"representations":[1],"of":[2],"audio":[3,14],"signals":[4],"often":[5],"resemble":[6],"texture":[7,23,45],"images.":[8,24],"This":[9],"paper":[10],"derives":[11],"a":[12],"simple":[13],"classification":[15,33,56],"algorithm":[16,26,48],"based":[17,42],"on":[18,43],"treating":[19],"sound":[20],"spectrograms":[21],"as":[22],"The":[25],"is":[27],"inspired":[28],"by":[29],"an":[30],"earlier":[31],"visual":[32],"scheme":[34],"particularly":[35],"efficient":[36],"at":[37],"classifying":[38],"textures.":[39],"While":[40],"solely":[41],"time-frequency":[44],"features,":[46],"the":[47],"achieves":[49],"surprisingly":[50],"good":[51],"performance":[52],"in":[53],"musical":[54],"instrument":[55],"experiments.":[57]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
