{"id":"https://openalex.org/W3015360161","doi":"https://doi.org/10.1109/icassp40776.2020.9054725","title":"End-To-End Auditory Object Recognition Via Inception Nucleus","display_name":"End-To-End Auditory Object Recognition Via Inception Nucleus","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015360161","doi":"https://doi.org/10.1109/icassp40776.2020.9054725","mag":"3015360161"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5050745506","display_name":"Mohammad K. Ebrahimpour","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Ebrahimpour","raw_affiliation_strings":["Electrical Engineering and Computer Science, UC Merced"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, UC Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040691907","display_name":"Timothy M. Shea","orcid":"https://orcid.org/0000-0001-5705-0904"},"institutions":[{"id":"https://openalex.org/I1310439424","display_name":"Accenture (Switzerland)","ror":"https://ror.org/041r3e346","country_code":"CH","type":"company","lineage":["https://openalex.org/I1310439424","https://openalex.org/I4210093804"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Timothy Shea","raw_affiliation_strings":["Accenture Labs"],"affiliations":[{"raw_affiliation_string":"Accenture Labs","institution_ids":["https://openalex.org/I1310439424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017602213","display_name":"Andreea Danielescu","orcid":"https://orcid.org/0000-0001-7460-2467"},"institutions":[{"id":"https://openalex.org/I1310439424","display_name":"Accenture (Switzerland)","ror":"https://ror.org/041r3e346","country_code":"CH","type":"company","lineage":["https://openalex.org/I1310439424","https://openalex.org/I4210093804"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreea Danielescu","raw_affiliation_strings":["Accenture Labs"],"affiliations":[{"raw_affiliation_string":"Accenture Labs","institution_ids":["https://openalex.org/I1310439424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050674828","display_name":"David C. Noelle","orcid":"https://orcid.org/0000-0003-3141-5658"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Noelle","raw_affiliation_strings":["Electrical Engineering and Computer Science, UC Merced"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, UC Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110868797","display_name":"Chris Kello","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Kello","raw_affiliation_strings":["Cognitive and Information Sciences, UC Merced"],"affiliations":[{"raw_affiliation_string":"Cognitive and Information Sciences, UC Merced","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050745506"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59229756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"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":0.9991000294685364,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7275885343551636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6413155198097229},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6094397306442261},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5919877290725708},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5306103825569153},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5199500322341919},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.48864203691482544},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48081839084625244},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.47847506403923035},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.47195497155189514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.457430899143219},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4286203682422638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275885343551636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413155198097229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6094397306442261},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5919877290725708},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5306103825569153},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5199500322341919},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.48864203691482544},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48081839084625244},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.47847506403923035},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47195497155189514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.457430899143219},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4286203682422638},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307894","display_name":"Accenture","ror":"https://ror.org/013g16z83"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1972567154","https://openalex.org/W1995562189","https://openalex.org/W2038484192","https://openalex.org/W2069943693","https://openalex.org/W2088850873","https://openalex.org/W2137028279","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2313745396","https://openalex.org/W2408093180","https://openalex.org/W2529337537","https://openalex.org/W2593451766","https://openalex.org/W2612445135","https://openalex.org/W2752782242","https://openalex.org/W2901459357","https://openalex.org/W2902444285","https://openalex.org/W2922086296","https://openalex.org/W2962756039","https://openalex.org/W2963232038","https://openalex.org/W2963446712","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2969335882","https://openalex.org/W4289288178","https://openalex.org/W4293665662","https://openalex.org/W4297775537","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6713548365","https://openalex.org/W6729831399","https://openalex.org/W6737664043","https://openalex.org/W6755726434"],"related_works":["https://openalex.org/W2100203012","https://openalex.org/W2353790262","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"approaches":[2],"to":[3,37,60,66,128],"auditory":[4,31],"object":[5],"recognition":[6,32],"are":[7],"traditionally":[8],"based":[9],"on":[10,83,107],"engineered":[11],"features":[12,39,130],"such":[13],"as":[14],"those":[15],"derived":[16],"from":[17],"the":[18,62,78,84,108,120],"spectrum":[19],"or":[20],"cepstrum.":[21],"More":[22],"recently,":[23],"end-":[24],"to-end":[25],"classification":[26,42,47],"systems":[27,33],"in":[28,45,88,119],"image":[29],"and":[30,43],"have":[34],"been":[35],"developed":[36],"learn":[38],"jointly":[40],"with":[41],"result":[44],"improved":[46],"accuracy.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53],"a":[54],"novel":[55],"end-to-end":[56],"deep":[57],"neural":[58],"network":[59,71],"map":[61],"raw":[63],"waveform":[64],"inputs":[65],"sound":[67],"class":[68],"labels.":[69],"Our":[70],"includes":[72],"an":[73],"\"inception":[74],"nucleus\"":[75],"that":[76,86,117,131],"optimizes":[77],"size":[79],"of":[80,113],"convolutional":[81],"filters":[82,118],"fly":[85],"results":[87,94],"reducing":[89],"engineering":[90],"efforts":[91],"dramatically.":[92],"Classification":[93],"compared":[95],"favorably":[96],"against":[97],"current":[98],"state-of-the-art":[99],"approaches,":[100],"besting":[101],"them":[102],"by":[103],"10.4":[104],"percentage":[105],"points":[106],"Ur-":[109],"bansound8k":[110],"dataset.":[111],"Analyses":[112],"learned":[114,124],"representations":[115],"revealed":[116],"earlier":[121],"hidden":[122],"layers":[123],"wavelet":[125],"like":[126],"transforms":[127],"extract":[129],"were":[132],"informative":[133],"for":[134],"classification.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}