{"id":"https://openalex.org/W2131185065","doi":"https://doi.org/10.1109/icassp.2008.4517574","title":"Musical Sound Separation Using Pitch-Based Labeling and Binary Time-Frequency Masking","display_name":"Musical Sound Separation Using Pitch-Based Labeling and Binary Time-Frequency Masking","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2131185065","doi":"https://doi.org/10.1109/icassp.2008.4517574","mag":"2131185065"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4517574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517574","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5101799190","display_name":"Yipeng Li","orcid":"https://orcid.org/0000-0001-9099-4077"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yipeng Li","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Michigan, OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Michigan, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Michigan, OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Michigan, OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101799190"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":3.4925,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93357488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"401","issue":null,"first_page":"173","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9976999759674072,"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":0.6821781396865845},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6214648485183716},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.544346809387207},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5413098335266113},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5309543013572693},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5264093279838562},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.45557111501693726},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.45244330167770386},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4458000063896179},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4325612187385559},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.310697466135025},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2054222822189331},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.15127447247505188},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09634199738502502},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08510145545005798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821781396865845},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6214648485183716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.544346809387207},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5413098335266113},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5309543013572693},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5264093279838562},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.45557111501693726},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.45244330167770386},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4458000063896179},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4325612187385559},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.310697466135025},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2054222822189331},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.15127447247505188},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09634199738502502},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08510145545005798},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2008.4517574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517574","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.2134","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.2134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Li-Wang.icassp08b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1575829986","https://openalex.org/W1596689267","https://openalex.org/W1607142029","https://openalex.org/W1902027874","https://openalex.org/W2022462917","https://openalex.org/W2042731730","https://openalex.org/W2106582496","https://openalex.org/W2139418888","https://openalex.org/W2149425615","https://openalex.org/W2152960355","https://openalex.org/W2162209287","https://openalex.org/W2185430646","https://openalex.org/W2319744969","https://openalex.org/W2561557072","https://openalex.org/W3216401400","https://openalex.org/W4256399001","https://openalex.org/W6635459212","https://openalex.org/W6636203886","https://openalex.org/W6686209566"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2100891835","https://openalex.org/W4372260329"],"abstract_inverted_index":{"Monaural":[0],"musical":[1],"sound":[2],"separation":[3],"attempts":[4],"to":[5,32],"segregate":[6],"different":[7],"instrument":[8,35],"lines":[9],"from":[10],"single-channel":[11],"polyphonic":[12],"music.":[13],"We":[14],"propose":[15],"a":[16,62],"system":[17,44,60],"that":[18],"decomposes":[19],"an":[20,26],"input":[21],"into":[22],"time-frequency":[23,38],"units":[24],"using":[25],"auditory":[27],"filterbank":[28],"and":[29,48],"utilizes":[30],"pitch":[31],"label":[33],"which":[34],"line":[36],"each":[37],"unit":[39],"is":[40,45],"assigned":[41],"to.":[42],"The":[43],"conceptually":[46],"simple":[47],"computationally":[49],"efficient.":[50],"Systematic":[51],"evaluation":[52],"shows":[53],"that,":[54],"despite":[55],"its":[56],"simplicity,":[57],"the":[58],"proposed":[59],"achieves":[61],"competitive":[63],"level":[64],"of":[65],"performance.":[66]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
