{"id":"https://openalex.org/W3183740155","doi":"https://doi.org/10.3390/sym13071296","title":"Dual Attention Network for Pitch Estimation of Monophonic Music","display_name":"Dual Attention Network for Pitch Estimation of Monophonic Music","publication_year":2021,"publication_date":"2021-07-19","ids":{"openalex":"https://openalex.org/W3183740155","doi":"https://doi.org/10.3390/sym13071296","mag":"3183740155"},"language":"en","primary_location":{"id":"doi:10.3390/sym13071296","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13071296","pdf_url":"https://www.mdpi.com/2073-8994/13/7/1296/pdf?version=1626924764","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/13/7/1296/pdf?version=1626924764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005542642","display_name":"Wenfang Ma","orcid":"https://orcid.org/0000-0002-2671-2773"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfang Ma","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing in Xinjiang, Urumqi 830046, China","School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing in Xinjiang, Urumqi 830046, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing in Xinjiang, Urumqi 830046, China","School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing in Xinjiang, Urumqi 830046, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Key Laboratory of Multilingual Information Technology in Xinjiang, Urumqi 830046, China","School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang, Urumqi 830046, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":1800,"currency":"CHF","value_usd":1944},"apc_paid":{"value":1800,"currency":"CHF","value_usd":1944},"fwci":0.1407,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4619776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"13","issue":"7","first_page":"1296","last_page":"1296"},"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":0.9984999895095825,"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":0.9944000244140625,"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":0.7635082006454468},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5664944648742676},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5030900835990906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4886358380317688},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.48023420572280884},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.45051684975624084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4352302551269531},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4344017803668976},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.4150194823741913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4102838635444641},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40811020135879517},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09329941868782043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635082006454468},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5664944648742676},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5030900835990906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4886358380317688},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.48023420572280884},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.45051684975624084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4352302551269531},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4344017803668976},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.4150194823741913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4102838635444641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40811020135879517},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09329941868782043},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/sym13071296","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13071296","pdf_url":"https://www.mdpi.com/2073-8994/13/7/1296/pdf?version=1626924764","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:416983d569874fceb48291e7fc929d1b","is_oa":true,"landing_page_url":"https://doaj.org/article/416983d569874fceb48291e7fc929d1b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 13, Iss 7, p 1296 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/sym13071296","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym13071296","pdf_url":"https://www.mdpi.com/2073-8994/13/7/1296/pdf?version=1626924764","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3183740155.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W146460917","https://openalex.org/W1496920063","https://openalex.org/W1504986446","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1965419851","https://openalex.org/W1975079546","https://openalex.org/W1990449877","https://openalex.org/W2034300186","https://openalex.org/W2091425152","https://openalex.org/W2095705004","https://openalex.org/W2096429026","https://openalex.org/W2118774185","https://openalex.org/W2296724634","https://openalex.org/W2407685581","https://openalex.org/W2514009036","https://openalex.org/W2516301810","https://openalex.org/W2567070169","https://openalex.org/W2586947700","https://openalex.org/W2664741028","https://openalex.org/W2752782242","https://openalex.org/W2766238477","https://openalex.org/W2773294482","https://openalex.org/W2774581901","https://openalex.org/W2788560150","https://openalex.org/W2891901715","https://openalex.org/W2897371647","https://openalex.org/W2902480954","https://openalex.org/W2920728711","https://openalex.org/W2921083967","https://openalex.org/W2938109705","https://openalex.org/W2939051810","https://openalex.org/W2949117887","https://openalex.org/W2949154855","https://openalex.org/W2955058313","https://openalex.org/W2962866891","https://openalex.org/W2963050807","https://openalex.org/W2963420686","https://openalex.org/W2963535133","https://openalex.org/W2963970792","https://openalex.org/W2964951804","https://openalex.org/W2965809241","https://openalex.org/W2970476707","https://openalex.org/W2972353749","https://openalex.org/W2972654834","https://openalex.org/W2973011366","https://openalex.org/W2973054567","https://openalex.org/W2991361823","https://openalex.org/W3015641245","https://openalex.org/W3038106538","https://openalex.org/W3038122926","https://openalex.org/W3096848254","https://openalex.org/W3118018449","https://openalex.org/W3165336848","https://openalex.org/W3191088441","https://openalex.org/W3192742126","https://openalex.org/W4288622715","https://openalex.org/W6630119264","https://openalex.org/W6674330103","https://openalex.org/W6697040288","https://openalex.org/W6844210595"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2040545019","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911"],"abstract_inverted_index":{"The":[0,185],"task":[1],"of":[2,37,49,54,77,122,133,187],"pitch":[3,22],"estimation":[4,23],"is":[5,61,97,111],"an":[6],"essential":[7],"step":[8],"in":[9],"many":[10],"audio":[11],"signal":[12],"processing":[13],"applications.":[14],"In":[15,90],"this":[16],"paper,":[17],"we":[18],"propose":[19],"a":[20,100,114,192,198],"data-driven":[21],"network,":[24],"the":[25,34,75,82,91,93,107,134,148,164,170,178,207,211,219,232],"Dual":[26,43],"Attention":[27,44],"Network":[28],"(DA-Net),":[29],"which":[30,73],"processes":[31],"directly":[32],"on":[33,70,210],"time-domain":[35],"samples":[36],"monophonic":[38],"music.":[39],"DA-Net":[40,60,175,188],"includes":[41,51],"six":[42],"Modules":[45],"(DA-Modules),":[46],"and":[47,57,66,87,106,129,137,168,213],"each":[48],"them":[50],"two":[52],"kinds":[53,121],"attention:":[55],"element-wise":[56,86,94,135],"channel-wise":[58,88,108,138],"attention.":[59,139],"to":[62,157,161,196,202,218],"perform":[63],"element":[64],"attention":[65,68,95,109,136,141,154,225],"channel":[67],"operations":[69],"convolution":[71],"features,":[72],"reflects":[74],"idea":[76],"\"symmetry\".":[78],"DA-Modules":[79],"can":[80,155],"model":[81],"semantic":[83],"interdependencies":[84],"between":[85],"features.":[89],"DA-Module,":[92],"mechanism":[96,110],"realized":[98,112],"by":[99,113,146],"Convolutional":[101],"Gated":[102],"Linear":[103],"Unit":[104],"(ConvGLU),":[105],"Squeeze-and-Excitation":[115],"(SE)":[116],"block.":[117],"We":[118,205],"explored":[119],"three":[120],"combination":[123],"modes":[124],"(serial":[125],"mode,":[126,128],"parallel":[127],"tightly":[130,228],"coupled":[131,229],"mode)":[132],"Element-wise":[140],"selectively":[142,162],"emphasizes":[143],"useful":[144,172],"features":[145,149,180],"re-weighting":[147],"at":[150],"all":[151],"positions.":[152],"Channel-wise":[153],"learn":[156],"use":[158],"global":[159,183],"information":[160],"emphasize":[163],"informative":[165],"feature":[166],"maps":[167],"suppress":[169],"less":[171],"ones.":[173],"Therefore,":[174],"adaptively":[176],"integrates":[177],"local":[179],"with":[181,227],"their":[182],"dependencies.":[184],"outputs":[186],"are":[189],"fed":[190],"into":[191],"fully":[193],"connected":[194],"layer":[195],"generate":[197],"360-dimensional":[199],"vector":[200],"corresponding":[201],"360":[203],"pitches.":[204],"trained":[206],"proposed":[208,223],"network":[209,226],"iKala":[212],"MDB-stem-synth":[214],"datasets,":[215],"respectively.":[216],"According":[217],"experimental":[220],"results,":[221],"our":[222],"dual":[224],"mode":[230],"achieved":[231],"best":[233],"performance.":[234]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
