{"id":"https://openalex.org/W3082096666","doi":"https://doi.org/10.1109/spcom50965.2020.9179600","title":"End-to-end audio-scene classification from raw audio: Multi time-frequency resolution CNN architecture for efficient representation learning","display_name":"End-to-end audio-scene classification from raw audio: Multi time-frequency resolution CNN architecture for efficient representation learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082096666","doi":"https://doi.org/10.1109/spcom50965.2020.9179600","mag":"3082096666"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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/A5000610513","display_name":"Tarun Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"T. Vijaya Kumar","raw_affiliation_strings":["Samsung R&D Institute, Bangalore (SRIB), India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore (SRIB), India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031638927","display_name":"R. Sundar","orcid":"https://orcid.org/0000-0002-8092-8401"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Shunmuga Sundar","raw_affiliation_strings":["Samsung R&D Institute, Bangalore (SRIB), India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore (SRIB), India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074975867","display_name":"Tilak Purohit","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tilak Purohit","raw_affiliation_strings":["International Institute of Information Technology - Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology - Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036811576","display_name":"V. Ramasubramanian","orcid":"https://orcid.org/0000-0002-0676-9174"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"V. Ramasubramanian","raw_affiliation_strings":["International Institute of Information Technology - Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology - Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000610513"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.7577,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70994075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"60","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":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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/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":0.9904999732971191,"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":0.7797371745109558},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.5510662794113159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297568440437317},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5250829458236694},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5122529864311218},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47579464316368103},{"id":"https://openalex.org/keywords/radio-spectrum","display_name":"Radio spectrum","score":0.47016069293022156},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4454708695411682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43593764305114746},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4357437193393707},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4201081395149231},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3720071315765381},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3541533946990967},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1605135202407837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12593328952789307},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10969513654708862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797371745109558},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.5510662794113159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297568440437317},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5250829458236694},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5122529864311218},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47579464316368103},{"id":"https://openalex.org/C92545706","wikidata":"https://www.wikidata.org/wiki/Q902174","display_name":"Radio spectrum","level":2,"score":0.47016069293022156},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4454708695411682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43593764305114746},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4357437193393707},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4201081395149231},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3720071315765381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3541533946990967},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1605135202407837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12593328952789307},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10969513654708862},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1666984270","https://openalex.org/W1995562189","https://openalex.org/W2097117768","https://openalex.org/W2147800946","https://openalex.org/W2163922914","https://openalex.org/W2398826216","https://openalex.org/W2529337537","https://openalex.org/W2593179621","https://openalex.org/W2618530766","https://openalex.org/W2794150026","https://openalex.org/W2808507676","https://openalex.org/W2962785008","https://openalex.org/W2962793908","https://openalex.org/W2995348821","https://openalex.org/W3028311979","https://openalex.org/W4289294465","https://openalex.org/W6674914833","https://openalex.org/W6712560600","https://openalex.org/W6734751391","https://openalex.org/W6756074776"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926","https://openalex.org/W2098934641"],"abstract_inverted_index":{"We":[0],"propose":[1],"and":[2,52,110,146,167],"study":[3],"a":[4,21,36,43,53,60,67,77],"novel":[5],"multi-temporal":[6,78,157],"CNN":[7,79,166],"architecture":[8,80,136],"for":[9,26,71,95,155,173],"end-to-end":[10,138],"`audio-scene":[11],"classification'":[12],"(ASC)":[13],"from":[14,115],"raw":[15,107],"audio":[16,108],"signal.":[17],"Conventional":[18],"CNNs":[19],"use":[20,76],"fixed":[22,44,48,54],"size":[23],"kernel":[24,83],"(whether":[25],"image":[27],"or":[28],"1-d":[29],"signal":[30,109],"classification)":[31],"which":[32],"corresponds":[33],"to":[34,69,86,103,118,130,137,143],"applying":[35],"filter":[37,41,97],"bank,":[38],"where":[39],"each":[40,89],"has":[42],"time-frequency":[45,62,73,101,127,132],"resolution":[46,102],"(i.e.,":[47],"duration":[49],"impulse":[50],"response":[51],"band-width":[55],"frequency":[56],"response),":[57],"importantly":[58],"with":[59,99],"specific":[61],"trade-off.":[63],"In":[64],"contrast,":[65],"in":[66,123,153],"way":[68],"allow":[70],"multiple":[72,82,96],"resolutions,":[74],"we":[75],"having":[81],"branches":[84],"(up":[85],"12":[87,160],"branches)":[88,161],"of":[90,125,159],"different":[91,100,131],"lengths,":[92],"thereby":[93],"allowing":[94],"banks":[98],"process":[104],"the":[105,156,163],"input":[106],"create":[111],"feature-maps":[112],"(e.g.":[113,150],"ranging":[114],"very":[116,119],"narrow-band":[117],"wide-band":[120],"spectrographic":[121],"maps":[122],"steps":[124],"fine":[126],"resolutions)":[128],"corresponding":[129],"trade-offs.":[133],"Applying":[134],"this":[135,174],"audio-scene":[139],"classification":[140],"is":[141],"shown":[142],"offer":[144],"consistent":[145],"significant":[147],"performance":[148],"enhancements":[149],"11-15%":[151],"absolute":[152],"accuracy":[154],"case":[158],"over":[162],"conventional":[164],"single-temporal":[165],"also":[168],"outperform":[169],"state-of":[170],"the-art":[171],"results":[172],"task.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}