{"id":"https://openalex.org/W2125276869","doi":"https://doi.org/10.1109/icassp.2011.5946313","title":"Combining HMM-based melody extraction and NMF-based soft masking for separating voice and accompaniment from monaural audio","display_name":"Combining HMM-based melody extraction and NMF-based soft masking for separating voice and accompaniment from monaural audio","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2125276869","doi":"https://doi.org/10.1109/icassp.2011.5946313","mag":"2125276869"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5100377674","display_name":"Yun Wang","orcid":"https://orcid.org/0009-0005-3803-7014"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100377674"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.9187,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7510147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/monaural","display_name":"Monaural","score":0.8788764476776123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8022509813308716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7102788686752319},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5246173143386841},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5245740413665771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3611697852611542}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8788764476776123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8022509813308716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102788686752319},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5246173143386841},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5245740413665771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3611697852611542},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5946313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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":20,"referenced_works":["https://openalex.org/W144548647","https://openalex.org/W1964208564","https://openalex.org/W2004554462","https://openalex.org/W2098446659","https://openalex.org/W2103031592","https://openalex.org/W2110644015","https://openalex.org/W2124539664","https://openalex.org/W2130911235","https://openalex.org/W2147455188","https://openalex.org/W2150113039","https://openalex.org/W2166209411","https://openalex.org/W2189429918","https://openalex.org/W2403272360","https://openalex.org/W6605891315","https://openalex.org/W6641567374","https://openalex.org/W6651361882","https://openalex.org/W6674722923","https://openalex.org/W6676956424","https://openalex.org/W6682433475","https://openalex.org/W6687632320"],"related_works":["https://openalex.org/W3128571556","https://openalex.org/W2005574340","https://openalex.org/W2374918184","https://openalex.org/W2125276869","https://openalex.org/W2402362233","https://openalex.org/W1543303981","https://openalex.org/W2786302331","https://openalex.org/W2187958048","https://openalex.org/W2158426391","https://openalex.org/W1881865575"],"abstract_inverted_index":{"Modern":[0],"monaural":[1],"voice":[2],"and":[3,15,46,51,55,67,80,99],"accompaniment":[4],"separation":[5,24],"systems":[6,25],"usually":[7],"consist":[8],"of":[9,63,71],"two":[10,34,86],"main":[11,20],"modules:":[12],"melody":[13,39,65,73],"extraction":[14,40,74],"time":[16],"frequency":[17],"masking.":[18,57,83],"A":[19],"distinction":[21],"between":[22],"different":[23],"lies":[26],"in":[27],"what":[28],"approaches":[29],"are":[30],"used":[31],"for":[32,38],"the":[33,61,69,92],"modules.":[35],"Popular":[36],"techniques":[37],"include":[41],"hidden":[42],"Markov":[43],"models":[44],"(HMMs)":[45],"non-negative":[47],"matrix":[48],"factorization":[49],"(NMF),":[50],"masking":[52],"includes":[53],"hard":[54],"soft":[56,82],"This":[58],"paper":[59],"investigates":[60],"flaw":[62],"NMF-based":[64,81],"extraction,":[66],"proposes":[68],"combination":[70],"HMM-based":[72],"(equipped":[75],"with":[76],"a":[77],"newly-defined":[78],"feature)":[79],"Evaluations":[84],"on":[85],"publicly":[87],"available":[88],"databases":[89],"show":[90],"that":[91],"proposed":[93],"system":[94],"reaches":[95],"state-of":[96],"the-art":[97],"performance":[98],"outperforms":[100],"several":[101],"other":[102],"combinations.":[103]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
