{"id":"https://openalex.org/W2141732083","doi":"https://doi.org/10.1109/icme.2005.1521554","title":"Feature Selection and Stacking for Robust Discrimination of Speech, Monophonic Singing, and Polyphonic Music","display_name":"Feature Selection and Stacking for Robust Discrimination of Speech, Monophonic Singing, and Polyphonic Music","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2141732083","doi":"https://doi.org/10.1109/icme.2005.1521554","mag":"2141732083"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","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/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"B. Schuller","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Inst. for Human-Machine Commun., Technische Univ. Munchen"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Technische Univ. Munchen","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020758553","display_name":"B.J.B. Schmitt","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"B.J.B. Schmitt","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Inst. for Human-Machine Commun., Technische Univ. Munchen"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Technische Univ. Munchen","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088855123","display_name":"Dejan Arsi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Arsic","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Inst. for Human-Machine Commun., Technische Univ. Munchen"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Technische Univ. Munchen","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112793493","display_name":"S.A. Reiter","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Reiter","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Inst. for Human-Machine Commun., Technische Univ. Munchen"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Technische Univ. Munchen","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088367992","display_name":"M. Lang","orcid":"https://orcid.org/0009-0001-8080-0010"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Lang","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Inst. for Human-Machine Commun., Technische Univ. Munchen"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Technische Univ. Munchen","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G. Rigoll","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Inst. for Human-Machine Commun., Technische Univ. Munchen"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Technische Univ. Munchen","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043060302"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.6213,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84743454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"840","last_page":"843"},"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":0.9988999962806702,"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":0.9868999719619751,"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":0.7802901268005371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6560140252113342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5444127917289734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5411372184753418},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5012602806091309},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4794982075691223},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.47233739495277405},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.46402838826179504},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.463580846786499},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4542056918144226},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4492274522781372},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.43455785512924194},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4254940152168274},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41698792576789856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802901268005371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6560140252113342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5444127917289734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5411372184753418},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5012602806091309},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4794982075691223},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.47233739495277405},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.46402838826179504},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.463580846786499},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4542056918144226},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4492274522781372},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.43455785512924194},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4254940152168274},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41698792576789856},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme.2005.1521554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.323.9530","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.323.9530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/05/05sch2.pdf","raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:76741","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-767412","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"},{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W1486187507","https://openalex.org/W1833279920","https://openalex.org/W2014915963","https://openalex.org/W2106055371","https://openalex.org/W2108603235","https://openalex.org/W2124867748","https://openalex.org/W2128838222","https://openalex.org/W2137667955","https://openalex.org/W2966207845","https://openalex.org/W6600593648","https://openalex.org/W6638563753","https://openalex.org/W6678836955","https://openalex.org/W6679311584"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W3135448569"],"abstract_inverted_index":{"In":[0],"this":[1,41],"work":[2],"we":[3,35,49,76,103],"strive":[4],"to":[5,23],"find":[6],"an":[7],"optimal":[8],"set":[9,54],"of":[10,16,46,60,65,74,85,116,127,131,148,158],"acoustic":[11,26],"features":[12,62],"for":[13,29],"the":[14,51,89,141,156,159],"discrimination":[15,146],"speech,":[17,128],"monophonic":[18],"singing,":[19],"and":[20,31,99,110,112,129],"polyphonic":[21],"music":[22],"robustly":[24],"segment":[25],"media":[27],"streams":[28],"annotation":[30],"interaction":[32],"purposes.":[33],"Furthermore":[34],"introduce":[36],"ensemble-based":[37],"classification":[38],"approaches":[39],"within":[40,88],"task.":[42,91],"From":[43],"a":[44,72,149],"basis":[45,73],"276":[47],"attributes":[48],"select":[50],"most":[52],"efficient":[53],"by":[55,63,79,108,118,124],"SVM":[56],"SFFS.":[57],"Additionally":[58],"relevance":[59],"single":[61,105],"calculation":[64],"information":[66],"gain":[67],"ratio":[68],"is":[69,122],"presented.":[70],"As":[71],"comparison":[75],"reduce":[77],"dimensionality":[78],"PCA.":[80],"We":[81],"show":[82],"extensive":[83],"analysis":[84],"different":[86],"classifiers":[87,117],"named":[90],"Among":[92],"these":[93],"are":[94],"Kernel":[95],"Machines,":[96],"Decision":[97],"Trees,":[98],"Bayesian":[100],"Classifiers.":[101],"Moreover":[102],"improve":[104],"classifier":[106],"performance":[107],"Bagging":[109],"Boosting,":[111],"finally":[113],"combine":[114],"strengths":[115],"StackingC.":[119],"The":[120,144],"database":[121],"formed":[123],"2,114":[125],"samples":[126],"singing":[130],"58":[132],"persons.":[133],"1,000":[134],"Music":[135],"clips":[136],"have":[137],"been":[138],"taken":[139],"from":[140],"MTV-Europe-Top-20":[142],"1980-2000.":[143],"outstanding":[145],"results":[147],"working":[150],"real":[151],"time":[152],"capable":[153],"implementation":[154],"stress":[155],"practicability":[157],"proposed":[160],"novel":[161],"ideas.":[162]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
