{"id":"https://openalex.org/W4385823161","doi":"https://doi.org/10.21437/interspeech.2023-2494","title":"MTANet: Multi-band Time-frequency Attention Network for Singing Melody Extraction from Polyphonic Music","display_name":"MTANet: Multi-band Time-frequency Attention Network for Singing Melody Extraction from Polyphonic Music","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823161","doi":"https://doi.org/10.21437/interspeech.2023-2494"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2494","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5101437986","display_name":"Yuan Gao","orcid":"https://orcid.org/0009-0004-7836-9120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066964166","display_name":"Liusong Wang","orcid":"https://orcid.org/0009-0008-0909-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liusong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956433","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0002-6932-6952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317921","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4826-629X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8636,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89148014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5396","last_page":"5400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9925000071525574,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.991599977016449,"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/polyphony","display_name":"Polyphony","score":0.9214941263198853},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.773632287979126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820916533470154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6755982637405396},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5964149832725525},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33709973096847534},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07493454217910767}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9214941263198853},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.773632287979126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820916533470154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6755982637405396},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5964149832725525},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33709973096847534},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07493454217910767},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2494","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2122830402","https://openalex.org/W178932670","https://openalex.org/W2935701729","https://openalex.org/W2130581557","https://openalex.org/W3192255518","https://openalex.org/W144548647","https://openalex.org/W162634215","https://openalex.org/W2124232593","https://openalex.org/W4287816566","https://openalex.org/W2098448993"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}
