{"id":"https://openalex.org/W2167665852","doi":"https://doi.org/10.1109/icassp.2008.4517534","title":"A background music detection method based on robust feature extraction","display_name":"A background music detection method based on robust feature extraction","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2167665852","doi":"https://doi.org/10.1109/icassp.2008.4517534","mag":"2167665852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4517534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517534","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5038974112","display_name":"Tomonori Izumitani","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomonori Izumitani","raw_affiliation_strings":["NTT Communication Science Laboratories, Astugi, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Astugi, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043759410","display_name":"Ryo Mukai","orcid":"https://orcid.org/0000-0003-1796-9232"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Mukai","raw_affiliation_strings":["NTT Communication Science Laboratories, Astugi, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Astugi, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunio Kashino","raw_affiliation_strings":["NTT Communication Science Laboratories, Astugi, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Astugi, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.2228,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87710843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"16"},"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":0.9997000098228455,"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":0.9929999709129333,"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":0.778226912021637},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7150028347969055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6615349650382996},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5311825275421143},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5259003043174744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141732692718506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49584922194480896},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.48711705207824707},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4842643141746521},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47580891847610474},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.44243958592414856},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.440576434135437},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.20685383677482605},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17330718040466309},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11234697699546814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07449987530708313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778226912021637},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7150028347969055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6615349650382996},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5311825275421143},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5259003043174744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141732692718506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49584922194480896},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.48711705207824707},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4842643141746521},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47580891847610474},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.44243958592414856},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.440576434135437},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.20685383677482605},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17330718040466309},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11234697699546814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07449987530708313},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":2,"locations":[{"id":"doi:10.1109/icassp.2008.4517534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517534","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.467.379","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.467.379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://202.114.89.42/resource/pdf/1452.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5299999713897705,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1607142029","https://openalex.org/W1975098367","https://openalex.org/W2029051663","https://openalex.org/W2085457662","https://openalex.org/W2086889779","https://openalex.org/W2106055371","https://openalex.org/W2119479037","https://openalex.org/W2121127941","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W2133824856","https://openalex.org/W2134123343","https://openalex.org/W2144345993","https://openalex.org/W4285719527","https://openalex.org/W6636203886"],"related_works":["https://openalex.org/W3176621072","https://openalex.org/W2995475466","https://openalex.org/W2356785732","https://openalex.org/W4239033281","https://openalex.org/W4380789568","https://openalex.org/W3105745662","https://openalex.org/W4210430843","https://openalex.org/W2571325231","https://openalex.org/W2003977768","https://openalex.org/W4316036082"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,18,72,82,89],"music":[3,25,37,108],"segment":[4],"detection":[5,20,79],"method":[6,56],"for":[7],"audio":[8],"signals.":[9],"Unlike":[10],"many":[11],"existing":[12],"methods,":[13],"ours":[14],"specifically":[15],"focuses":[16],"on":[17],"background-music":[19],"task,":[21],"that":[22],"is,":[23],"detecting":[24],"used":[26],"in":[27,48],"background":[28],"of":[29,58,74],"main":[30],"sounds.":[31],"This":[32],"task":[33],"is":[34,38],"important":[35],"because":[36],"almost":[39],"always":[40],"overlapped":[41],"by":[42,109],"speech":[43,102],"or":[44],"other":[45],"environmental":[46],"sounds":[47],"visual":[49],"materials":[50],"such":[51],"as":[52,93,95],"TV":[53],"programs.":[54],"Our":[55],"consists":[57],"feature":[59],"extraction,":[60],"dimension":[61],"reduction,":[62],"and":[63],"statistical":[64],"discrimination":[65],"steps.":[66],"For":[67],"each":[68],"step,":[69,86],"we":[70,87],"analyzed":[71],"set":[73],"methods":[75],"to":[76],"maximize":[77],"the":[78,100,106],"accuracy.":[80],"With":[81],"simple":[83],"post":[84],"processing":[85],"achieved":[88],"framewise":[90],"error":[91],"rate":[92],"low":[94],"8":[96],"%":[97],"even":[98],"when":[99],"mixed":[101],"was":[103],"louder":[104],"than":[105],"target":[107],"10dB.":[110]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
