{"id":"https://openalex.org/W2978506400","doi":"https://doi.org/10.1109/ijcnn.2019.8852128","title":"Music Classification using an Improved CRNN with Multi-Directional Spatial Dependencies in Both Time and Frequency Dimensions","display_name":"Music Classification using an Improved CRNN with Multi-Directional Spatial Dependencies in Both Time and Frequency Dimensions","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978506400","doi":"https://doi.org/10.1109/ijcnn.2019.8852128","mag":"2978506400"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5100422381","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8637-8375"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Department of Computer Science, University of Wyoming"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wyoming","institution_ids":["https://openalex.org/I12834331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000641921","display_name":"Suresh Muknahallipatna","orcid":"https://orcid.org/0000-0003-4153-524X"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suresh Muknahallipatna","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Wyoming"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112486746","display_name":"Maohong Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maohong Fan","raw_affiliation_strings":["Dept. of Chem. Eng., University of Wyoming, Laramie, WY, US"],"affiliations":[{"raw_affiliation_string":"Dept. of Chem. Eng., University of Wyoming, Laramie, WY, US","institution_ids":["https://openalex.org/I12834331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077922843","display_name":"Austin Okray","orcid":null},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Okray","raw_affiliation_strings":["Department of Computer Science, University of Wyoming"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wyoming","institution_ids":["https://openalex.org/I12834331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023655697","display_name":"Chao Lan","orcid":"https://orcid.org/0000-0003-2526-7206"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Lan","raw_affiliation_strings":["Department of Computer Science, University of Wyoming"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wyoming","institution_ids":["https://openalex.org/I12834331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100422381"],"corresponding_institution_ids":["https://openalex.org/I12834331"],"apc_list":null,"apc_paid":null,"fwci":1.4927,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83398797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9958999752998352,"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":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.7097540497779846},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5416254997253418},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49941277503967285},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4766060709953308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41479143500328064},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.41358333826065063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3567083477973938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3307086229324341},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2793642282485962},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12912076711654663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12226277589797974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097540497779846},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5416254997253418},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49941277503967285},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4766060709953308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41479143500328064},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.41358333826065063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3567083477973938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3307086229324341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2793642282485962},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12912076711654663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12226277589797974},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1922658220","https://openalex.org/W2038678505","https://openalex.org/W2042390666","https://openalex.org/W2059652044","https://openalex.org/W2107789863","https://openalex.org/W2127870748","https://openalex.org/W2137028279","https://openalex.org/W2161381512","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2198584637","https://openalex.org/W2295991281","https://openalex.org/W2399607803","https://openalex.org/W2414894569","https://openalex.org/W2580221632","https://openalex.org/W2591013610","https://openalex.org/W2592168896","https://openalex.org/W2593179621","https://openalex.org/W2604509013","https://openalex.org/W2604959036","https://openalex.org/W2725868244","https://openalex.org/W2783639327","https://openalex.org/W2799205108","https://openalex.org/W2962965465","https://openalex.org/W2963451564","https://openalex.org/W3098729331","https://openalex.org/W3102568015","https://openalex.org/W3105202226","https://openalex.org/W4300957348","https://openalex.org/W6638205174","https://openalex.org/W6640137754","https://openalex.org/W6676071220","https://openalex.org/W6678969435","https://openalex.org/W6696901769","https://openalex.org/W6712735165","https://openalex.org/W6715395060","https://openalex.org/W6732646663","https://openalex.org/W6734751391","https://openalex.org/W6736327223","https://openalex.org/W6740333300","https://openalex.org/W6747536483","https://openalex.org/W6785932716"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W2578422401"],"abstract_inverted_index":{"In":[0,53],"music":[1,30,74,90,105,116],"classification":[2,51],"tasks,":[3],"Convolutional":[4],"Recurrent":[5],"Neural":[6],"Network":[7],"(CRNN)":[8],"has":[9],"achieved":[10],"state-of-the-art":[11,102],"performance":[12],"on":[13,87,114],"several":[14,100],"data":[15,91,117],"sets.":[16],"However,":[17],"the":[18,43,120],"current":[19],"CRNN":[20,62,98],"technique":[21,60],"only":[22],"uses":[23],"RNN":[24],"to":[25,49],"extract":[26],"spatial":[27,71],"dependency":[28],"of":[29,73],"signal":[31,75],"in":[32,63,76,82],"its":[33,38],"time":[34,78],"dimension":[35],"but":[36],"not":[37],"frequency":[39,80],"dimension.":[40],"We":[41],"hypothesize":[42],"latter":[44],"can":[45],"be":[46],"additionally":[47],"exploited":[48],"improve":[50],"performance.":[52],"this":[54],"paper,":[55],"we":[56],"propose":[57],"an":[58],"improved":[59],"called":[61],"Time":[64],"and":[65,79,99],"Frequency":[66],"dimensions":[67,81],"(CRNN-TF),":[68],"which":[69],"captures":[70],"dependencies":[72],"both":[77],"multiple":[83],"directions.":[84],"Experimental":[85],"studies":[86],"three":[88],"real-world":[89],"sets":[92,118],"show":[93],"that":[94],"CRNN-TF":[95,111],"consistently":[96],"outperforms":[97],"other":[101],"deep":[103],"learning-based":[104],"classifiers.":[106],"Our":[107],"results":[108],"also":[109],"suggest":[110],"is":[112],"transferable":[113],"small":[115],"via":[119],"fine-tuning":[121],"technique.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}