{"id":"https://openalex.org/W3128825287","doi":"https://doi.org/10.1109/icassp39728.2021.9414049","title":"Structure-Aware Audio-to-Score Alignment Using Progressively Dilated Convolutional Neural Networks","display_name":"Structure-Aware Audio-to-Score Alignment Using Progressively Dilated Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3128825287","doi":"https://doi.org/10.1109/icassp39728.2021.9414049","mag":"3128825287"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.00382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034426967","display_name":"Ruchit Agrawal","orcid":"https://orcid.org/0000-0002-3609-9589"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ruchit Agrawal","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, UK","[Queen Mary University of London,Centre for Digital Music,UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"[Queen Mary University of London,Centre for Digital Music,UK]","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045832504","display_name":"Daniel Wolff","orcid":"https://orcid.org/0000-0003-4550-1442"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Daniel Wolff","raw_affiliation_strings":["Institute for Research and Coordination in Acoustics/Music, Paris, France","Institute for Research and Coordination in Acoustics/Music,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research and Coordination in Acoustics/Music, Paris, France","institution_ids":["https://openalex.org/I35345632"]},{"raw_affiliation_string":"Institute for Research and Coordination in Acoustics/Music,Paris,France","institution_ids":["https://openalex.org/I35345632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Institute for Research and Coordination in Acoustics/Music, Paris, France","Institute for Research and Coordination in Acoustics/Music,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research and Coordination in Acoustics/Music, Paris, France","institution_ids":["https://openalex.org/I35345632"]},{"raw_affiliation_string":"Institute for Research and Coordination in Acoustics/Music,Paris,France","institution_ids":["https://openalex.org/I35345632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034426967"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0166756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"571","last_page":"575"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.998199999332428,"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":0.9973000288009644,"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":0.773910403251648},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7156475782394409},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.5982897281646729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5696670413017273},{"id":"https://openalex.org/keywords/dilation","display_name":"Dilation (metric space)","score":0.5460063815116882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4979379177093506},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49634677171707153},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48487600684165955},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.47169044613838196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4284963607788086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08334770798683167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773910403251648},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7156475782394409},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.5982897281646729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5696670413017273},{"id":"https://openalex.org/C2780757906","wikidata":"https://www.wikidata.org/wiki/Q5276676","display_name":"Dilation (metric space)","level":2,"score":0.5460063815116882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4979379177093506},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49634677171707153},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48487600684165955},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.47169044613838196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4284963607788086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08334770798683167},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.00382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00382","pdf_url":"https://arxiv.org/pdf/2102.00382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97873","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97873","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97873/2/Dixon%20Structure-Aware%20Audio%202021%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"mag:3128825287","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.00382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/73480","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/73480","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"doi:10.48550/arxiv.2102.00382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.00382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/43pd-kc06","is_oa":true,"landing_page_url":"https://doi.org/10.17023/43pd-kc06","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.00382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00382","pdf_url":"https://arxiv.org/pdf/2102.00382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3128825287.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W20389641","https://openalex.org/W93815243","https://openalex.org/W123154089","https://openalex.org/W1582055164","https://openalex.org/W2032085270","https://openalex.org/W2042390666","https://openalex.org/W2111256709","https://openalex.org/W2135057920","https://openalex.org/W2191779130","https://openalex.org/W2206887674","https://openalex.org/W2395462034","https://openalex.org/W2397379298","https://openalex.org/W2397907422","https://openalex.org/W2404620398","https://openalex.org/W2406388223","https://openalex.org/W2529229741","https://openalex.org/W2614256707","https://openalex.org/W2806987872","https://openalex.org/W2890559714","https://openalex.org/W2963116179","https://openalex.org/W2963551352","https://openalex.org/W2963840672","https://openalex.org/W2982297432","https://openalex.org/W2989853363","https://openalex.org/W2990825719","https://openalex.org/W3046184278","https://openalex.org/W3103753223","https://openalex.org/W3117303186","https://openalex.org/W3125095875","https://openalex.org/W3186755767","https://openalex.org/W6603836127","https://openalex.org/W6605019438","https://openalex.org/W6696085341","https://openalex.org/W6711855267","https://openalex.org/W6712946787","https://openalex.org/W6713718600","https://openalex.org/W6728440854","https://openalex.org/W6745851314","https://openalex.org/W6752173134","https://openalex.org/W6753035467","https://openalex.org/W6764724119","https://openalex.org/W6770058728","https://openalex.org/W6781639648","https://openalex.org/W6893480188","https://openalex.org/W6912863972","https://openalex.org/W7000504209"],"related_works":["https://openalex.org/W3162873781","https://openalex.org/W3046467284","https://openalex.org/W2962687637","https://openalex.org/W135040384","https://openalex.org/W2176316098","https://openalex.org/W2575406636","https://openalex.org/W2902572630","https://openalex.org/W3094965760","https://openalex.org/W3032959444","https://openalex.org/W3163045350","https://openalex.org/W2395971734","https://openalex.org/W2802272416","https://openalex.org/W2951015274","https://openalex.org/W2260672250","https://openalex.org/W2949174760","https://openalex.org/W3207932315","https://openalex.org/W190031129","https://openalex.org/W1587677015","https://openalex.org/W2938722449","https://openalex.org/W3129631327"],"abstract_inverted_index":{"The":[0],"identification":[1],"of":[2,18,24,46,78,88],"structural":[3],"differences":[4,36],"between":[5,37],"a":[6,13,30,43],"music":[7,25,47],"performance":[8,41],"and":[9,40,67,70,97],"the":[10,38,76,95],"score":[11,39],"is":[12],"challenging":[14],"yet":[15],"integral":[16],"step":[17],"audio-to-score":[19,109],"alignment,":[20],"an":[21],"important":[22],"subtask":[23],"information":[26],"retrieval.":[27],"We":[28,82],"present":[29],"novel":[31],"method":[32,55],"to":[33,63],"detect":[34],"such":[35],"for":[42,107],"given":[44],"piece":[45],"using":[48],"progressively":[49],"dilated":[50],"convolutional":[51],"neural":[52],"networks.":[53],"Our":[54],"incorporates":[56],"varying":[57],"dilation":[58],"rates":[59],"at":[60],"different":[61],"layers":[62],"capture":[64],"both":[65],"short-term":[66],"long-term":[68],"context,":[69],"can":[71],"be":[72],"employed":[73],"successfully":[74],"in":[75],"presence":[77],"limited":[79],"annotated":[80],"data.":[81],"conduct":[83],"experiments":[84],"on":[85],"audio":[86],"recordings":[87],"real":[89],"performances":[90],"that":[91,101],"differ":[92],"structurally":[93],"from":[94],"score,":[96],"our":[98,102],"results":[99],"demonstrate":[100],"models":[103],"outperform":[104],"standard":[105],"methods":[106],"structure-aware":[108],"alignment.":[110]},"counts_by_year":[],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}