{"id":"https://openalex.org/W2938109705","doi":"https://doi.org/10.1109/icassp.2019.8683630","title":"CNN Based Two-stage Multi-resolution End-to-end Model for Singing Melody Extraction","display_name":"CNN Based Two-stage Multi-resolution End-to-end Model for Singing Melody Extraction","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2938109705","doi":"https://doi.org/10.1109/icassp.2019.8683630","mag":"2938109705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5053429340","display_name":"Ming-Tso Chen","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":"Ming-Tso Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"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/A5111926913","display_name":"Bojun Li","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":"Bo-Jun Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"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"],"raw_orcid":null,"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3365,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89098545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1005","last_page":"1009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919999837875366,"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/singing","display_name":"Singing","score":0.7893427610397339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7021991014480591},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6105643510818481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5128741264343262},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.46733415126800537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35835087299346924},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2368970513343811}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7893427610397339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021991014480591},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6105643510818481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5128741264343262},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.46733415126800537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35835087299346924},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2368970513343811},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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:10.1109/icassp.2019.8683630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1496920063","https://openalex.org/W1526336542","https://openalex.org/W1967815448","https://openalex.org/W1976069042","https://openalex.org/W2034300186","https://openalex.org/W2054139811","https://openalex.org/W2057052076","https://openalex.org/W2059652044","https://openalex.org/W2097117768","https://openalex.org/W2107124638","https://openalex.org/W2124539664","https://openalex.org/W2161632835","https://openalex.org/W2296724634","https://openalex.org/W2331927446","https://openalex.org/W2398826216","https://openalex.org/W2407685581","https://openalex.org/W2516301810","https://openalex.org/W2571951934","https://openalex.org/W2774707525","https://openalex.org/W2799452163","https://openalex.org/W2963669405","https://openalex.org/W2964177567","https://openalex.org/W6674914833","https://openalex.org/W6697040288","https://openalex.org/W6712560600","https://openalex.org/W6714030504","https://openalex.org/W6731524272","https://openalex.org/W6746914816"],"related_works":["https://openalex.org/W3207249698","https://openalex.org/W1528909574","https://openalex.org/W2122830402","https://openalex.org/W4223953616","https://openalex.org/W2921857201","https://openalex.org/W3107474891","https://openalex.org/W169038075","https://openalex.org/W3207038517","https://openalex.org/W3207340675","https://openalex.org/W2973046048"],"abstract_inverted_index":{"Inspired":[0],"by":[1,50],"human":[2],"hearing":[3],"perception,":[4],"we":[5],"propose":[6],"a":[7],"two-stage":[8],"multi-resolution":[9,33,39,71],"end-to-end":[10],"model":[11,30,105],"for":[12],"singing":[13],"melody":[14],"extraction":[15],"in":[16,110],"this":[17],"paper.":[18],"The":[19,35,62,84],"convolutional":[20],"neural":[21],"network":[22],"(CNN)":[23],"is":[24],"the":[25,28,77,103],"core":[26],"of":[27,57,67,89,97,113],"proposed":[29,104],"to":[31],"generate":[32],"representations.":[34],"1-D":[36,52,63],"and":[37,43,53,60,81],"2-D":[38,54,85],"analysis":[40],"on":[41],"waveform":[42],"spectrogram-like":[44,72],"graph":[45],"are":[46],"successively":[47],"carried":[48],"out":[49,112],"using":[51],"CNN":[55],"kernels":[56,66,88],"different":[58,68,90,98],"lengths":[59,69],"sizes.":[61],"CNNs":[64,86],"with":[65,87],"produce":[70],"graphs":[73],"without":[74],"suffering":[75],"from":[76,94],"trade-off":[78],"between":[79],"spectral":[80],"temporal":[82],"resolutions.":[83],"sizes":[91],"extract":[92],"features":[93],"spectro-temporal":[95],"envelopes":[96],"scales.":[99],"Experiment":[100],"results":[101],"show":[102],"outperforms":[106],"three":[107,111],"compared":[108],"systems":[109],"five":[114],"public":[115],"databases.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}