{"id":"https://openalex.org/W2799452163","doi":"https://doi.org/10.1109/icassp.2018.8461483","title":"A Hybrid Neural Network Based on the Duplex Model of Pitch Perception for Singing Melody Extraction","display_name":"A Hybrid Neural Network Based on the Duplex Model of Pitch Perception for Singing Melody Extraction","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2799452163","doi":"https://doi.org/10.1109/icassp.2018.8461483","mag":"2799452163"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5109110186","display_name":"Hsin Hung Chou","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":"Hsin Chou","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/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":"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":1.4964,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83171479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"385"},"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":0.9993000030517578,"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":0.9962000250816345,"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/singing","display_name":"Singing","score":0.8197401762008667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7257720232009888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6915191411972046},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6444458365440369},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6072299480438232},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6066634654998779},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.5253293514251709},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.44942355155944824},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.42664653062820435},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.41462892293930054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3624088764190674},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29432666301727295},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2852029800415039},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12411195039749146},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07946881651878357}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8197401762008667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7257720232009888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915191411972046},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6444458365440369},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6072299480438232},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6066634654998779},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.5253293514251709},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.44942355155944824},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.42664653062820435},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.41462892293930054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3624088764190674},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29432666301727295},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2852029800415039},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12411195039749146},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07946881651878357},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":31,"referenced_works":["https://openalex.org/W126774805","https://openalex.org/W1496920063","https://openalex.org/W1526336542","https://openalex.org/W1967815448","https://openalex.org/W1971146038","https://openalex.org/W1976069042","https://openalex.org/W2002525568","https://openalex.org/W2019986537","https://openalex.org/W2034300186","https://openalex.org/W2043694038","https://openalex.org/W2057052076","https://openalex.org/W2058535166","https://openalex.org/W2059260101","https://openalex.org/W2088273711","https://openalex.org/W2103662883","https://openalex.org/W2107124638","https://openalex.org/W2119599673","https://openalex.org/W2124539664","https://openalex.org/W2161632835","https://openalex.org/W2396684454","https://openalex.org/W2406544397","https://openalex.org/W2407685581","https://openalex.org/W2571951934","https://openalex.org/W2577202280","https://openalex.org/W3193040400","https://openalex.org/W4241659927","https://openalex.org/W6605126489","https://openalex.org/W6712557957","https://openalex.org/W6714030504","https://openalex.org/W6731524272","https://openalex.org/W6732421929"],"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/W2144119193","https://openalex.org/W3144523531"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,49,69],"build":[4],"up":[5],"a":[6],"hybrid":[7],"neural":[8],"network":[9],"(NN)":[10],"for":[11],"singing":[12,65,111],"melody":[13,66,112],"extraction":[14],"from":[15,88],"polyphonic":[16],"music":[17],"by":[18],"imitating":[19],"human":[20,24],"pitch":[21,29,86],"perception.":[22],"For":[23],"hearing,":[25],"there":[26],"are":[27,44],"two":[28],"perception":[30,87],"models,":[31],"the":[32,36,62,71,75,80,85,92,96,102],"spectral":[33,93],"model":[34,94],"and":[35,57],"temporal":[37,97],"model,":[38,82],"in":[39,61,110],"accordance":[40],"with":[41],"whether":[42],"harmonics":[43,90],"resolved":[45],"or":[46],"not.":[47],"Here,":[48],"first":[50],"use":[51],"NNs":[52,72],"to":[53,73,78],"implement":[54],"individual":[55],"models":[56],"evaluate":[58],"their":[59],"performance":[60],"task":[63],"of":[64,91],"extraction.":[67,113],"Then,":[68],"combine":[70],"constitute":[74],"composite":[76,104],"NN":[77,105],"simulate":[79],"duplex":[81],"which":[83],"complements":[84],"unresolved":[89],"using":[95],"model.":[98],"Simulation":[99],"results":[100],"show":[101],"proposed":[103],"outperforms":[106],"other":[107],"conventional":[108],"methods":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
