{"id":"https://openalex.org/W3015683396","doi":"https://doi.org/10.1109/icassp40776.2020.9054711","title":"Audio Sound Determination Using Feature Space Attention Based Convolution Recurrent Neural Network","display_name":"Audio Sound Determination Using Feature Space Attention Based Convolution Recurrent Neural Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015683396","doi":"https://doi.org/10.1109/icassp40776.2020.9054711","mag":"3015683396"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054711","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/A5091584895","display_name":"Xianjun Xia","orcid":"https://orcid.org/0000-0001-5277-6634"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xianjun Xia","raw_affiliation_strings":["Machine Learning Group, MediaLab, Tencent"],"affiliations":[{"raw_affiliation_string":"Machine Learning Group, MediaLab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000806577","display_name":"Jingjing Pan","orcid":"https://orcid.org/0000-0001-7362-0778"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Pan","raw_affiliation_strings":["China University of Mining and Technology"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Machine Learning Group, MediaLab, Tencent"],"affiliations":[{"raw_affiliation_string":"Machine Learning Group, MediaLab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091584895"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59321922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"25","issue":null,"first_page":"3382","last_page":"3386"},"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":0.9973000288009644,"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":0.986299991607666,"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/convolution","display_name":"Convolution (computer science)","score":0.7682355642318726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.723596453666687},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5796535015106201},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5794268846511841},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5465736389160156},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5092369318008423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5055661201477051},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4959155023097992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43699905276298523},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42549145221710205},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.41387292742729187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3849022388458252},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33580952882766724},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.27337318658828735},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10482299327850342},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06465214490890503}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7682355642318726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723596453666687},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5796535015106201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5794268846511841},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5465736389160156},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5092369318008423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5055661201477051},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4959155023097992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43699905276298523},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42549145221710205},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.41387292742729187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3849022388458252},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33580952882766724},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27337318658828735},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10482299327850342},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06465214490890503},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icassp40776.2020.9054711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054711","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1650531274","https://openalex.org/W1665214252","https://openalex.org/W1902237438","https://openalex.org/W2065529590","https://openalex.org/W2118463056","https://openalex.org/W2141399712","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2619771377","https://openalex.org/W2745616976","https://openalex.org/W2752592287","https://openalex.org/W2752693731","https://openalex.org/W2763761345","https://openalex.org/W2775505379","https://openalex.org/W2794821752","https://openalex.org/W2810934215","https://openalex.org/W2962958286","https://openalex.org/W2964121744","https://openalex.org/W2964947054","https://openalex.org/W3009927332","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6680834391","https://openalex.org/W6744964450","https://openalex.org/W6766900982"],"related_works":["https://openalex.org/W2970216048","https://openalex.org/W2167955297","https://openalex.org/W2097297745","https://openalex.org/W3197541072","https://openalex.org/W2052253960","https://openalex.org/W2147802381","https://openalex.org/W2982233537","https://openalex.org/W2036586713","https://openalex.org/W2509918103","https://openalex.org/W3148519004"],"abstract_inverted_index":{"The":[0,68],"classification":[1,18],"framework":[2],"has":[3,33],"been":[4,35],"popularly":[5],"adopted":[6],"to":[7,63,73,91,95,123],"perform":[8,64],"sound":[9],"event":[10,66,127],"detection.":[11,67],"However,":[12],"the":[13,27,56,75,80,84,92,98,107,115,119,124],"existing":[14,125],"neural":[15,52],"network":[16,53],"based":[17,19,49],"approaches":[20],"treat":[21],"each":[22,60,101],"feature":[23,31,46,61,85,102],"dimension":[24,62],"equally":[25],"and":[26],"varying":[28,57],"influence":[29],"of":[30,59,100,118],"dimensions":[32],"not":[34],"taken":[36],"into":[37],"consideration.":[38],"To":[39],"deal":[40],"with":[41],"this,":[42],"we":[43],"propose":[44],"a":[45],"space":[47,86],"attention":[48,87],"convolution":[50,69],"recurrent":[51],"approach":[54,121],"utilizing":[55],"importance":[58,99],"acoustic":[65,126],"layers":[70],"are":[71],"used":[72],"extract":[74],"high":[76],"level":[77],"information":[78],"from":[79],"audio":[81],"signals.":[82],"Then":[83],"scheme":[88],"is":[89],"applied":[90],"extracted":[93],"features":[94],"automatically":[96],"determine":[97],"dimension.":[103],"Experimental":[104],"results":[105],"on":[106],"latest":[108],"TUT":[109],"Sound":[110],"Event":[111],"2017":[112],"dataset":[113],"demonstrate":[114],"improved":[116],"performance":[117],"proposed":[120],"compared":[122],"detection":[128],"systems.":[129]},"counts_by_year":[{"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"}