{"id":"https://openalex.org/W2517119754","doi":"https://doi.org/10.1109/icme.2016.7552987","title":"Reducing manual labeling in singing voice detection: An active learning approach","display_name":"Reducing manual labeling in singing voice detection: An active learning approach","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2517119754","doi":"https://doi.org/10.1109/icme.2016.7552987","mag":"2517119754"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2016.7552987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552987","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 Multimedia and Expo (ICME)","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/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113104770","display_name":"Xiangyi Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyi Feng","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077962542","display_name":"Min Xue","orcid":"https://orcid.org/0000-0002-8136-6551"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Xue","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100318193"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.08657854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9973999857902527,"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":0.9959999918937683,"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":0.7741132974624634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7138188481330872},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7113053798675537},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6172945499420166},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6052775979042053},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6033825874328613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5793671607971191},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5503093004226685},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5455739498138428},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.512101411819458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48652762174606323},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.45943042635917664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38607877492904663},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3649342656135559},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24797338247299194},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06755509972572327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741132974624634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7138188481330872},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7113053798675537},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6172945499420166},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6052775979042053},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6033825874328613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5793671607971191},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5503093004226685},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5455739498138428},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.512101411819458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48652762174606323},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.45943042635917664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38607877492904663},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3649342656135559},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24797338247299194},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06755509972572327},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2016.7552987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552987","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W55723365","https://openalex.org/W65296863","https://openalex.org/W173389330","https://openalex.org/W1570504315","https://openalex.org/W1583001605","https://openalex.org/W1945892259","https://openalex.org/W1964208564","https://openalex.org/W2057038428","https://openalex.org/W2107131609","https://openalex.org/W2116241760","https://openalex.org/W2123169318","https://openalex.org/W2124539664","https://openalex.org/W2124867748","https://openalex.org/W2153635508","https://openalex.org/W2156063339","https://openalex.org/W2157569565","https://openalex.org/W2293137601","https://openalex.org/W4206723194","https://openalex.org/W4285719527","https://openalex.org/W6602276745","https://openalex.org/W6602647452","https://openalex.org/W6634309418","https://openalex.org/W6640767421","https://openalex.org/W6677466130","https://openalex.org/W6697162658","https://openalex.org/W6949199605"],"related_works":["https://openalex.org/W2056314584","https://openalex.org/W1492505081","https://openalex.org/W1986633584","https://openalex.org/W2976807053","https://openalex.org/W184546935","https://openalex.org/W2909115059","https://openalex.org/W2943886396","https://openalex.org/W3203050224","https://openalex.org/W42414577","https://openalex.org/W3020745670"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,52],"solve":[3],"the":[4,21,26,47,59,67,72,78],"bottleneck":[5],"of":[6,49,74,80],"tedious":[7],"and":[8,38,55],"time-consuming":[9],"manual":[10],"labeling":[11],"in":[12,16,77],"singing":[13,81],"voice":[14,82],"detection,":[15],"this":[17],"paper":[18],"we":[19],"integrate":[20],"active":[22,43,75],"learning":[23,30,44,76],"mechanism":[24],"into":[25],"conventional":[27],"SVM-based":[28],"supervised":[29],"algorithm.":[31],"By":[32],"selecting":[33],"most":[34],"informative":[35],"unlabeled":[36],"samples":[37,51],"asking":[39],"for":[40],"human":[41],"annotation,":[42],"substantially":[45],"reduces":[46],"number":[48],"training":[50],"be":[53],"labeled":[54],"meanwhile":[56],"obtains":[57],"almost":[58],"same":[60],"frame-level":[61],"vocal/non-vocal":[62],"classification":[63],"performance.":[64],"Experiments":[65],"on":[66],"public":[68],"MIR-1K":[69],"database":[70],"demonstrate":[71],"effectiveness":[73],"task":[79],"detection.":[83]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}