{"id":"https://openalex.org/W2019457474","doi":"https://doi.org/10.1145/1032604.1032620","title":"Automatic classification of speech and music using neural networks","display_name":"Automatic classification of speech and music using neural networks","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W2019457474","doi":"https://doi.org/10.1145/1032604.1032620","mag":"2019457474"},"language":"en","primary_location":{"id":"doi:10.1145/1032604.1032620","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1032604.1032620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM international workshop on Multimedia databases","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/A5108382819","display_name":"M. Kashif Saeed Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"M. Kashif Saeed Khan","raw_affiliation_strings":["King Fahd Univ. of Petroleum and Minerals, Dhahran, Saudi Arabia","King Fahd University of Petroleum & Minerals, Dhahran Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Fahd Univ. of Petroleum and Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]},{"raw_affiliation_string":"King Fahd University of Petroleum & Minerals, Dhahran Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062511117","display_name":"Wasfi G. Al-Khatib","orcid":"https://orcid.org/0000-0002-6760-3506"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Wasfi G. Al-Khatib","raw_affiliation_strings":["King Fahd Univ. of Petroleum and Minerals, Dhahran, Saudi Arabia","King Fahd University of Petroleum & Minerals, Dhahran Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Fahd Univ. of Petroleum and Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]},{"raw_affiliation_string":"King Fahd University of Petroleum & Minerals, Dhahran Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057263563","display_name":"Muhammad Moinuddin","orcid":"https://orcid.org/0000-0003-4735-0692"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Muhammad Moinuddin","raw_affiliation_strings":["King Fahd Univ. of Petroleum and Minerals, Dhahran, Saudi Arabia","King Fahd University of Petroleum & Minerals, Dhahran Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Fahd Univ. of Petroleum and Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]},{"raw_affiliation_string":"King Fahd University of Petroleum & Minerals, Dhahran Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2867,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.56552662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"99"},"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":0.9976000189781189,"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":0.9819999933242798,"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":0.7755089998245239},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6681363582611084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6374425888061523},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5929327011108398},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5671349167823792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4811031222343445},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.46813520789146423},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4566754996776581},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.43968087434768677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4178123474121094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755089998245239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6681363582611084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6374425888061523},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5929327011108398},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5671349167823792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4811031222343445},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.46813520789146423},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4566754996776581},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.43968087434768677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4178123474121094},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1032604.1032620","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1032604.1032620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM international workshop on Multimedia databases","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W58940029","https://openalex.org/W176670434","https://openalex.org/W1502874967","https://openalex.org/W1600222083","https://openalex.org/W1833279920","https://openalex.org/W2029261284","https://openalex.org/W2106055371","https://openalex.org/W2106339924","https://openalex.org/W2124776405","https://openalex.org/W2124864596","https://openalex.org/W2127936745","https://openalex.org/W2128838222","https://openalex.org/W2149799225","https://openalex.org/W2151305614","https://openalex.org/W2482342158","https://openalex.org/W2603415636","https://openalex.org/W3150877489","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2136232598"],"abstract_inverted_index":{"The":[0,20],"importance":[1],"of":[2,36,62,67,107],"automatic":[3],"discrimination":[4],"between":[5,50],"speech":[6,29,51],"signals":[7,10],"and":[8,52,65],"music":[9,31,53],"has":[11],"evolved":[12],"as":[13,28,93],"a":[14,94],"research":[15],"topic":[16],"over":[17],"recent":[18],"years.":[19],"need":[21],"to":[22,48,74],"classify":[23],"audio":[24,83],"into":[25],"categories":[26],"such":[27],"or":[30],"is":[32],"an":[33],"important":[34],"aspect":[35],"many":[37],"multimedia":[38],"document":[39],"retrieval":[40],"systems.":[41],"Several":[42],"approaches":[43],"have":[44,78,86,99],"been":[45,79],"previously":[46,81],"used":[47,80,87],"discriminate":[49],"data.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"the":[60,63,68,105],"use":[61],"mean":[64],"variance":[66],"discrete":[69],"wavelet":[70],"transform":[71],"in":[72],"addition":[73],"other":[75],"features":[76],"that":[77,103],"for":[82],"classification.":[84],"We":[85],"Multi-Layer":[88],"Perceptron":[89],"(MLP)":[90],"Neural":[91],"Networks":[92],"classifier.":[95],"Our":[96],"initial":[97],"tests":[98],"shown":[100],"encouraging":[101],"results":[102],"indicate":[104],"viability":[106],"our":[108],"approach.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
