{"id":"https://openalex.org/W168903045","doi":"https://doi.org/10.21437/interspeech.2009-330","title":"Singing voice detection in polyphonic music using predominant pitch","display_name":"Singing voice detection in polyphonic music using predominant pitch","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W168903045","doi":"https://doi.org/10.21437/interspeech.2009-330","mag":"168903045"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-330","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110122222","display_name":"Vishweshwara Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishweshwara Rao","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101840472","display_name":"S. Ramakrishnan","orcid":"https://orcid.org/0000-0001-5506-1570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Ramakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084496610","display_name":"Preeti Rao","orcid":"https://orcid.org/0000-0002-2842-8450"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Rao","raw_affiliation_strings":["Indian Inst. of Technology, Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Inst. of Technology, Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1134"},"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":0.9991999864578247,"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":0.9980999827384949,"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/singing","display_name":"Singing","score":0.7908745408058167},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.7677044868469238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6891301274299622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6822432279586792},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5966126322746277},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5940596461296082},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4789186716079712},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4621736407279968},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.44468018412590027},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44000017642974854},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3850927948951721},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3714197874069214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36746400594711304},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20931100845336914},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1807919442653656}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7908745408058167},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.7677044868469238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6891301274299622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822432279586792},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5966126322746277},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5940596461296082},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4789186716079712},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4621736407279968},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.44468018412590027},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44000017642974854},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3850927948951721},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3714197874069214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36746400594711304},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20931100845336914},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1807919442653656},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2009-330","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.847.3373","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.847.3373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.ee.iitb.ac.in/web//files/publications/RaoSPS2009.pdf","raw_type":"text"},{"id":"pmh:oai:dsapce.library.iitb.ac.in:100/2474","is_oa":false,"landing_page_url":"http://dspace.library.iitb.ac.in/xmlui/handle/10054/15808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400899","display_name":"DSpace (IIT Bombay)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162827531","host_organization_name":"Indian Institute of Technology Bombay","host_organization_lineage":["https://openalex.org/I162827531"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th INTERSPEECH 2009 Conference,Brighton, ENGLAND,SEP 06-10, 2009","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W173389330","https://openalex.org/W1570504315","https://openalex.org/W1833279920","https://openalex.org/W1964208564","https://openalex.org/W2026197045","https://openalex.org/W2107990538","https://openalex.org/W2116849392","https://openalex.org/W2154242587","https://openalex.org/W2168249484"],"related_works":["https://openalex.org/W2939490483","https://openalex.org/W3146151004","https://openalex.org/W2141992701","https://openalex.org/W2051008990","https://openalex.org/W2371980090","https://openalex.org/W2372033758","https://openalex.org/W2374084765","https://openalex.org/W2387668796","https://openalex.org/W2575117052","https://openalex.org/W2355766903"],"abstract_inverted_index":{"This":[0],"paper":[1],"demonstrates":[2],"the":[3,10,44,48,52,96],"superiority":[4],"of":[5,12,47,51,90],"energy-based":[6,28],"features":[7,29],"derived":[8],"from":[9],"knowledge":[11],"predominant-pitch,":[13],"for":[14,87,94],"singing":[15,53],"voice":[16,54,104],"detection":[17,89,105],"in":[18],"polyphonic":[19],"music":[20,80],"over":[21],"commonly":[22],"used":[23],"spectral":[24,58],"features.":[25],"However,":[26],"such":[27,40],"tend":[30],"to":[31,39,61,76],"misclassify":[32],"loud,":[33],"pitched":[34],"instruments.":[35],"To":[36],"provide":[37],"robustness":[38],"accompaniment":[41],"we":[42],"exploit":[43],"relative":[45],"instability":[46],"pitch":[49],"contour":[50],"by":[55],"attenuating":[56],"harmonic":[57],"content":[59],"belonging":[60],"stable-pitch":[62],"instruments,":[63],"using":[64],"sinusoidal":[65],"modeling.":[66],"The":[67],"obtained":[68],"feature":[69],"shows":[70],"high":[71],"classification":[72],"accuracy":[73],"when":[74],"applied":[75],"north":[77],"Indian":[78],"classical":[79],"data":[81],"and":[82],"is":[83],"also":[84],"found":[85],"suitable":[86],"automatic":[88],"vocal-instrumental":[91],"boundaries":[92],"required":[93],"smoothing":[95],"frame-level":[97],"classifier":[98],"decisions.":[99],"Index":[100],"Terms:":[101],"audio":[102],"segmentation,":[103],"1.":[106]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}