{"id":"https://openalex.org/W2906289885","doi":"https://doi.org/10.1109/msp.2018.2875511","title":"Audiovisual Analysis of Music Performances: Overview of an Emerging Field","display_name":"Audiovisual Analysis of Music Performances: Overview of an Emerging Field","publication_year":2018,"publication_date":"2018-12-25","ids":{"openalex":"https://openalex.org/W2906289885","doi":"https://doi.org/10.1109/msp.2018.2875511","mag":"2906289885"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2018.2875511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2018.2875511","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-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/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["Department of Computer Science, University of Rochester, New York"],"raw_orcid":"https://orcid.org/0000-0002-8334-9974","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, New York","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie (UPMC), Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie (UPMC), Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022063970","display_name":"Cynthia C. S. Liem","orcid":"https://orcid.org/0000-0002-5385-7695"},"institutions":[{"id":"https://openalex.org/I3129625411","display_name":"Royal Conservatory The Hague","ror":"https://ror.org/01mwwwn80","country_code":"NL","type":"education","lineage":["https://openalex.org/I3129625411"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cynthia C.S. Liem","raw_affiliation_strings":["Classical piano performance, Royal Conservatoire, The Hague, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5385-7695","affiliations":[{"raw_affiliation_string":"Classical piano performance, Royal Conservatoire, The Hague, The Netherlands","institution_ids":["https://openalex.org/I3129625411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["Rutgers University, Piscataway, New Jersey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, New Jersey","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705959","display_name":"Gaurav Sharma","orcid":"https://orcid.org/0000-0001-9735-9519"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Sharma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Department of Computer Science, and Department of Biostatistics and Computational Biology, University of Rochester, New York"],"raw_orcid":"https://orcid.org/0000-0001-9735-9519","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Department of Computer Science, and Department of Biostatistics and Computational Biology, University of Rochester, New York","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102749436"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":0.831,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.74949442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":"1","first_page":"63","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.6962159276008606},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6577516198158264},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5237928628921509},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45873773097991943},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45749056339263916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4571338891983032},{"id":"https://openalex.org/keywords/music-perception","display_name":"Music perception","score":0.43287983536720276},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43066591024398804},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41848060488700867},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.37466445565223694},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.2287742793560028},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.17053672671318054},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1305398941040039},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07286331057548523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962159276008606},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6577516198158264},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5237928628921509},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45873773097991943},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45749056339263916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4571338891983032},{"id":"https://openalex.org/C2987788386","wikidata":"https://www.wikidata.org/wiki/Q476590","display_name":"Music perception","level":3,"score":0.43287983536720276},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43066591024398804},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41848060488700867},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.37466445565223694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2287742793560028},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.17053672671318054},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1305398941040039},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07286331057548523},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":3,"locations":[{"id":"doi:10.1109/msp.2018.2875511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2018.2875511","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02287983v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-02287983","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Magazine, 2019, 36 (1), pp.63-73","raw_type":"Journal articles"},{"id":"pmh:oai:tudelft.nl:uuid:f7eb6deb-9c22-4355-b3f0-7ebc373a9e81","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:f7eb6deb-9c22-4355-b3f0-7ebc373a9e81","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5157521015","display_name":null,"funder_award_id":"1741472","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G783743583","display_name":null,"funder_award_id":"1471472","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1534806","https://openalex.org/W52610099","https://openalex.org/W1525931151","https://openalex.org/W1579979987","https://openalex.org/W1583585676","https://openalex.org/W1982796564","https://openalex.org/W1986602091","https://openalex.org/W1992479490","https://openalex.org/W2030511115","https://openalex.org/W2040448642","https://openalex.org/W2053652187","https://openalex.org/W2066170275","https://openalex.org/W2094430176","https://openalex.org/W2096042855","https://openalex.org/W2150159182","https://openalex.org/W2157110803","https://openalex.org/W2171819471","https://openalex.org/W2278943195","https://openalex.org/W2282853955","https://openalex.org/W2313960143","https://openalex.org/W2524365899","https://openalex.org/W2554620633","https://openalex.org/W2651884604","https://openalex.org/W2707117233","https://openalex.org/W2730531294","https://openalex.org/W2759171953","https://openalex.org/W2771678900","https://openalex.org/W2772625679","https://openalex.org/W2962756039","https://openalex.org/W2963066677","https://openalex.org/W3101943858","https://openalex.org/W4293665662","https://openalex.org/W6602120865","https://openalex.org/W6683296933","https://openalex.org/W6729831399","https://openalex.org/W6741152592","https://openalex.org/W6746598215","https://openalex.org/W6911855565","https://openalex.org/W6949316916","https://openalex.org/W7071105756"],"related_works":["https://openalex.org/W1975359510","https://openalex.org/W4312624015","https://openalex.org/W1496727373","https://openalex.org/W2020952589","https://openalex.org/W1833351015","https://openalex.org/W1580526244","https://openalex.org/W1564601668","https://openalex.org/W2365659558","https://openalex.org/W4252085734","https://openalex.org/W2350061705"],"abstract_inverted_index":{"In":[0],"the":[1,26,34,71],"physical":[2],"sciences":[3],"and":[4,51],"engineering":[5],"domains,":[6],"music":[7,19,37,59],"has":[8],"traditionally":[9],"been":[10],"considered":[11],"an":[12],"acoustic":[13,72],"phenomenon.":[14],"From":[15],"a":[16,31,55],"perceptual":[17],"viewpoint,":[18],"is":[20],"naturally":[21],"associated":[22],"with":[23],"hearing,":[24],"i.e.,":[25],"audio":[27,65],"modality.":[28],"Moreover,":[29],"for":[30],"long":[32],"time,":[33],"majority":[35],"of":[36,74],"recordings":[38],"were":[39],"distributed":[40],"through":[41],"audio-only":[42],"media,":[43],"such":[44],"as":[45],"vinyl":[46],"records,":[47],"cassettes,":[48],"compact":[49],"discs,":[50],"mp3":[52],"files.":[53],"As":[54],"consequence,":[56],"existing":[57],"automated":[58],"analysis":[60],"approaches":[61],"predominantly":[62],"focus":[63],"on":[64],"signals":[66],"that":[67],"represent":[68],"information":[69],"from":[70],"rendering":[73],"music.":[75]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
