{"id":"https://openalex.org/W2406972062","doi":"https://doi.org/10.1109/icassp.2016.7471716","title":"Predominant melody extraction from vocal polyphonic music signal by combined spectro-temporal method","display_name":"Predominant melody extraction from vocal polyphonic music signal by combined spectro-temporal method","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2406972062","doi":"https://doi.org/10.1109/icassp.2016.7471716","mag":"2406972062"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5046259198","display_name":"M Gurunath Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"M. Gurunath Reddy","raw_affiliation_strings":["Indian Institute of Technology Delhi, New Delhi, Delhi, IN"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, New Delhi, Delhi, IN","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048234263","display_name":"K. Sreenivasa Rao","orcid":"https://orcid.org/0000-0002-2186-0419"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Sreenivasa Rao","raw_affiliation_strings":["School of Information Technology, Indian Institute of Technology, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046259198"],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.4762221,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64733675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9904000163078308,"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/polyphony","display_name":"Polyphony","score":0.8516872525215149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7997783422470093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6296898722648621},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45427781343460083},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43541407585144043},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4333184063434601},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.41539716720581055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3560844659805298},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3410111367702484},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32143089175224304},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06529587507247925}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8516872525215149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7997783422470093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6296898722648621},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45427781343460083},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43541407585144043},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4333184063434601},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.41539716720581055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3560844659805298},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3410111367702484},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32143089175224304},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06529587507247925},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W175070741","https://openalex.org/W1496437476","https://openalex.org/W1496971974","https://openalex.org/W1976069042","https://openalex.org/W2022668263","https://openalex.org/W2023800933","https://openalex.org/W2035852710","https://openalex.org/W2059443479","https://openalex.org/W2067265757","https://openalex.org/W2070126228","https://openalex.org/W2112844139","https://openalex.org/W2134039779","https://openalex.org/W2140304104","https://openalex.org/W2161632835","https://openalex.org/W2164098335","https://openalex.org/W2166209411","https://openalex.org/W2168103573","https://openalex.org/W2396073362","https://openalex.org/W2397818963","https://openalex.org/W6629718326","https://openalex.org/W6712185337"],"related_works":["https://openalex.org/W2349264490","https://openalex.org/W2106094068","https://openalex.org/W2121987127","https://openalex.org/W1889793303","https://openalex.org/W4240250933","https://openalex.org/W2534386362","https://openalex.org/W2159113005","https://openalex.org/W2516392987","https://openalex.org/W2042145419","https://openalex.org/W2406972062"],"abstract_inverted_index":{"A":[0],"combined":[1],"spectro-temporal":[2],"based":[3],"method":[4,98],"is":[5,64,82],"proposed":[6,19,97],"to":[7],"derive":[8],"the":[9,18,60,88,92,96],"predominant":[10],"melody":[11,54,80,101],"from":[12],"vocal":[13,21,34,100],"polyphonic":[14],"music":[15],"signals.":[16],"In":[17],"method,":[20],"(voiced)":[22],"and":[23,87],"non-vocal":[24],"(unvoiced)":[25],"segments":[26,35,63],"are":[27,36],"determined":[28],"by":[29,42,66],"strength":[30],"of":[31,59,79,95],"excitation.":[32],"The":[33,53,77],"further":[37],"divided":[38],"into":[39],"voiced":[40,61],"notes":[41],"detecting":[43],"their":[44],"onsets":[45],"using":[46,67],"transition":[47],"cues":[48],"present":[49,56],"in":[50,57,74,84],"spectral":[51],"domain.":[52,76],"contour":[55],"each":[58],"note":[62],"obtained":[65],"an":[68],"adaptive":[69],"zero":[70],"frequency":[71],"filtering":[72],"(ZFF)":[73],"time":[75],"process":[78],"extraction":[81],"provided":[83],"more":[85],"detail":[86],"initial":[89],"results":[90],"showed":[91],"potential":[93],"use":[94],"for":[99],"extraction.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}