{"id":"https://openalex.org/W2963535133","doi":"https://doi.org/10.1109/icassp.2019.8682389","title":"A Streamlined Encoder/decoder Architecture for Melody Extraction","display_name":"A Streamlined Encoder/decoder Architecture for Melody Extraction","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963535133","doi":"https://doi.org/10.1109/icassp.2019.8682389","mag":"2963535133"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682389","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/A5102906755","display_name":"Tsung\u2010Han Hsieh","orcid":"https://orcid.org/0009-0005-2177-7059"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Han Hsieh","raw_affiliation_strings":["Data Science Degree Program, National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Degree Program, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5089,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97413111,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech 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":0.996399998664856,"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":0.8351107835769653},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6640501022338867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6548157930374146},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5777298808097839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48894229531288147},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.48049676418304443},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4776686131954193},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4289543926715851},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4227829575538635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3890182673931122},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15743854641914368},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13492339849472046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351107835769653},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6640501022338867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6548157930374146},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5777298808097839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48894229531288147},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.48049676418304443},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4776686131954193},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4289543926715851},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4227829575538635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3890182673931122},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15743854641914368},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13492339849472046},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682389","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2001426554","https://openalex.org/W2007664495","https://openalex.org/W2109770219","https://openalex.org/W2149180301","https://openalex.org/W2161632835","https://openalex.org/W2206275834","https://openalex.org/W2296704011","https://openalex.org/W2296724634","https://openalex.org/W2406222150","https://openalex.org/W2407685581","https://openalex.org/W2571951934","https://openalex.org/W2577202280","https://openalex.org/W2612711960","https://openalex.org/W2624413595","https://openalex.org/W2730332314","https://openalex.org/W2773294482","https://openalex.org/W2902480954","https://openalex.org/W2920728711","https://openalex.org/W2963158112","https://openalex.org/W2963249619","https://openalex.org/W2963351448","https://openalex.org/W2963454111","https://openalex.org/W2963881378","https://openalex.org/W2964177567","https://openalex.org/W2964289981","https://openalex.org/W2964309882","https://openalex.org/W4302076919","https://openalex.org/W6697040288","https://openalex.org/W6697285287","https://openalex.org/W6714030504","https://openalex.org/W6731524272","https://openalex.org/W6732421929","https://openalex.org/W6737829220","https://openalex.org/W6739879593","https://openalex.org/W6746836464","https://openalex.org/W6750630487","https://openalex.org/W6756648248","https://openalex.org/W6760299066"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"Melody":[0],"extraction":[1,132,136],"in":[2,59],"polyphonic":[3],"musical":[4],"audio":[5],"is":[6,23],"important":[7],"for":[8,25,40,99],"music":[9],"signal":[10],"processing.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15,44,79],"propose":[16,80],"a":[17,37,81,96,109],"novel":[18],"streamlined":[19],"encoder/decoder":[20],"network":[21,90],"that":[22],"designed":[24],"the":[26,47,57,67,85,89,93,119,123,138,141],"task.":[27],"We":[28,61],"make":[29,104],"two":[30],"technical":[31],"contributions.":[32],"First,":[33],"drawing":[34],"inspiration":[35],"from":[36],"state-of-the-art":[38,68],"model":[39],"semantic":[41],"pixel-wise":[42],"segmentation,":[43],"pass":[45],"through":[46],"pooling":[48,51],"indices":[49],"between":[50],"and":[52,74,103,133],"un-pooling":[53],"layers":[54,73],"to":[55,66,83,91,107,117],"localize":[56],"melody":[58,97,124,131,135],"frequency.":[60],"can":[62],"achieve":[63],"result":[64],"close":[65],"with":[69],"much":[70],"fewer":[71],"convolutional":[72],"simpler":[75],"convolution":[76],"modules.":[77],"Second,":[78],"way":[82],"use":[84,108],"bottleneck":[86],"layer":[87],"of":[88,95,114,122,140],"estimate":[92],"existence":[94],"line":[98],"each":[100],"time":[101],"frame,":[102],"it":[105],"possible":[106],"simple":[110],"argmax":[111],"function":[112],"instead":[113],"ad-hoc":[115],"thresholding":[116],"get":[118],"final":[120],"estimation":[121],"line.":[125],"Our":[126],"experiments":[127],"on":[128],"both":[129],"vocal":[130],"general":[134],"validate":[137],"effectiveness":[139],"proposed":[142],"model.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}