{"id":"https://openalex.org/W3015608758","doi":"https://doi.org/10.1109/icassp40776.2020.9053059","title":"A Multi-Dilation and Multi-Resolution Fully Convolutional Network for Singing Melody Extraction","display_name":"A Multi-Dilation and Multi-Resolution Fully Convolutional Network for Singing Melody Extraction","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015608758","doi":"https://doi.org/10.1109/icassp40776.2020.9053059","mag":"3015608758"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5101168953","display_name":"Ping Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ping Gao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062645618","display_name":"Cheng-You You","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-You You","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101168953"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":2.1215,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87682686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"551","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11447","display_name":"Blind Source Separation Techniques","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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/spectrogram","display_name":"Spectrogram","score":0.8330587148666382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7285450100898743},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7213306427001953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6719977855682373},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.5619980692863464},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5279024243354797},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4360443353652954},{"id":"https://openalex.org/keywords/auditory-cortex","display_name":"Auditory cortex","score":0.43323618173599243},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38843950629234314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35791921615600586},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2434689998626709},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.08600515127182007}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8330587148666382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285450100898743},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7213306427001953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6719977855682373},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.5619980692863464},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5279024243354797},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4360443353652954},{"id":"https://openalex.org/C2780297895","wikidata":"https://www.wikidata.org/wiki/Q18676","display_name":"Auditory cortex","level":2,"score":0.43323618173599243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38843950629234314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35791921615600586},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2434689998626709},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.08600515127182007},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2001426554","https://openalex.org/W2054139811","https://openalex.org/W2161632835","https://openalex.org/W2168103573","https://openalex.org/W2407685581","https://openalex.org/W2559597482","https://openalex.org/W2659365108","https://openalex.org/W2799213142","https://openalex.org/W2799452163","https://openalex.org/W2902480954","https://openalex.org/W2916798096","https://openalex.org/W2920728711","https://openalex.org/W2938109705","https://openalex.org/W2940262938","https://openalex.org/W2963158112","https://openalex.org/W2963446712","https://openalex.org/W2963535133","https://openalex.org/W3012391395","https://openalex.org/W3193040400","https://openalex.org/W6714030504","https://openalex.org/W6756648248","https://openalex.org/W6760299066","https://openalex.org/W6761630670"],"related_works":["https://openalex.org/W2936488316","https://openalex.org/W2059299633","https://openalex.org/W2732542196","https://openalex.org/W2940977206","https://openalex.org/W2995914718","https://openalex.org/W3156786002","https://openalex.org/W2977314777","https://openalex.org/W2969680539","https://openalex.org/W2518599539","https://openalex.org/W4307883119"],"abstract_inverted_index":{"Each":[0],"human":[1],"cognitive":[2],"function":[3],"involves":[4],"bottom-up":[5,22,29,74,97],"and":[6,33,42,65,75],"top-down":[7,24,76,99],"processes.":[8,25],"Several":[9],"methods":[10],"have":[11],"been":[12],"proposed":[13,88,93],"for":[14,80],"singing":[15,81],"melody":[16,82],"extraction":[17],"by":[18,39],"emphasizing":[19,95],"either":[20,96],"the":[21,28,37,40,43,60,63,73,87],"or":[23,98],"For":[26],"hearing,":[27,79],"processes":[30],"include":[31],"spectral":[32],"spectro-temporal":[34,56],"decomposition":[35,58],"of":[36,59,62,78],"sound":[38,64],"cochlea":[41],"auditory":[44],"cortex.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"a":[51,66],"neural":[52],"network,":[53],"which":[54],"includes":[55],"multi-resolution":[57],"log-spectrogram":[61],"semantic":[67],"segmentation":[68],"model":[69,89],"to":[70],"respectively":[71],"address":[72],"processing":[77],"extraction.":[83],"Simulation":[84],"results":[85],"show":[86],"outperforms":[90],"all":[91,103],"previously":[92],"methods,":[94],"processing,":[100],"in":[101],"almost":[102],"objective":[104],"evaluation":[105],"metrics.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
