{"id":"https://openalex.org/W2148609665","doi":"https://doi.org/10.1109/cbmi.2008.4564943","title":"Feature extraction for speech and music discrimination","display_name":"Feature extraction for speech and music discrimination","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2148609665","doi":"https://doi.org/10.1109/cbmi.2008.4564943","mag":"2148609665"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi.2008.4564943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2008.4564943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Workshop on Content-Based Multimedia Indexing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://bura.brunel.ac.uk/bitstream/2438/2427/1/Feature%20extraction%20for%20speech%20and%20music%20discrimination.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066119228","display_name":"Huiyu Zhou","orcid":"https://orcid.org/0000-0003-1634-9840"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiyu Zhou","raw_affiliation_strings":["Brunel University, Uxbridge, Middlesex, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brunel University, Uxbridge, Middlesex, United Kingdom","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113638173","display_name":"Abdul Sadka","orcid":null},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abdul Sadka","raw_affiliation_strings":["Brunel University, Uxbridge, Middlesex, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brunel University, Uxbridge, Middlesex, United Kingdom","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083182498","display_name":"Richard Jiang","orcid":"https://orcid.org/0000-0003-1721-9474"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard M. Jiang","raw_affiliation_strings":["Brunel University, Uxbridge, Middlesex, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brunel University, Uxbridge, Middlesex, United Kingdom","institution_ids":["https://openalex.org/I59433898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59433898"],"apc_list":null,"apc_paid":null,"fwci":2.6335,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90496332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"173"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832469940185547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7516025304794312},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7417275309562683},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6964123845100403},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6232593059539795},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6201198101043701},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5918155908584595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151451826095581},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4592255651950836},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.43667131662368774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832469940185547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7516025304794312},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7417275309562683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6964123845100403},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6232593059539795},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6201198101043701},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5918155908584595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151451826095581},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4592255651950836},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.43667131662368774},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cbmi.2008.4564943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2008.4564943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Workshop on Content-Based Multimedia Indexing","raw_type":"proceedings-article"},{"id":"pmh:oai:bura.brunel.ac.uk:2438/2427","is_oa":true,"landing_page_url":"http://bura.brunel.ac.uk/handle/2438/2427","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/2427/1/Feature%20extraction%20for%20speech%20and%20music%20discrimination.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.427.2396","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.427.2396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bura.brunel.ac.uk/bitstream/2438/2427/1/Feature extraction for speech and music discrimination.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.lancs.ac.uk:134375","is_oa":false,"landing_page_url":"https://eprints.lancs.ac.uk/id/eprint/134375/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Contribution in Book/Report/Proceedings"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/1b50aa14-b39b-4c3b-b812-74fd90a5f196","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/1b50aa14-b39b-4c3b-b812-74fd90a5f196","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhou, H, Sadka, A & Jiang, R M 2008, 'Feature extraction for speech and music discrimination', Paper presented at International Workshop on Content-based Multimedia Indexing, London, United Kingdom, 01/06/2008 - 01/06/2008 pp. 170-173.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:bura.brunel.ac.uk:2438/2427","is_oa":true,"landing_page_url":"http://bura.brunel.ac.uk/handle/2438/2427","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/2427/1/Feature%20extraction%20for%20speech%20and%20music%20discrimination.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2148609665.pdf","grobid_xml":"https://content.openalex.org/works/W2148609665.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1550027367","https://openalex.org/W1964726488","https://openalex.org/W2018097742","https://openalex.org/W2055910046","https://openalex.org/W2106339924","https://openalex.org/W2119479037","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W2137075158","https://openalex.org/W2159105055","https://openalex.org/W2166803312","https://openalex.org/W2482342158","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2335896301","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W2137764249","https://openalex.org/W3006618853","https://openalex.org/W2253066076","https://openalex.org/W2295636786","https://openalex.org/W2399492946","https://openalex.org/W2578092491","https://openalex.org/W2018086531"],"abstract_inverted_index":{"Driven":[0],"by":[1,73],"the":[2,35,45,58,75,78,97,101,108],"demand":[3],"of":[4,47,70,77,83,104],"information":[5],"retrieval,":[6],"video":[7],"editing":[8],"and":[9,23],"human-computer":[10],"interface,":[11],"in":[12,65,87,107],"this":[13],"paper":[14],"we":[15],"propose":[16],"a":[17,31],"novel":[18],"spectral":[19],"feature":[20,80,99],"for":[21],"music":[22],"speech":[24],"discrimination.":[25],"This":[26],"scheme":[27],"attempts":[28],"to":[29,42],"simulate":[30],"biological":[32],"model":[33],"using":[34],"averaged":[36],"cepstrum,":[37],"where":[38],"human":[39],"perception":[40],"tends":[41],"pick":[43],"up":[44],"areas":[46],"large":[48],"cepstral":[49],"changes.":[50],"The":[51,89],"cepstrum":[52],"data":[53],"that":[54,82,96],"is":[55],"away":[56],"from":[57],"mean":[59],"value":[60],"will":[61],"be":[62],"exponentially":[63],"reduced":[64],"magnitude.":[66],"We":[67],"conduct":[68],"experiments":[69],"music/speech":[71,105],"discrimination":[72],"comparing":[74],"performance":[76],"proposed":[79,85,98],"with":[81],"previously":[84],"features":[86],"classification.":[88],"dynamic":[90],"time":[91],"warping":[92],"based":[93],"classification":[94,106],"verifies":[95],"has":[100],"best":[102],"quality":[103],"test":[109],"database.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}