{"id":"https://openalex.org/W4387543615","doi":"https://doi.org/10.1145/3616195.3616206","title":"Onset Detection for String Instruments Using Bidirectional Temporal and Convolutional Recurrent Networks","display_name":"Onset Detection for String Instruments Using Bidirectional Temporal and Convolutional Recurrent Networks","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4387543615","doi":"https://doi.org/10.1145/3616195.3616206"},"language":"en","primary_location":{"id":"doi:10.1145/3616195.3616206","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616195.3616206","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616206","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616206","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056171040","display_name":"M. Tomczak","orcid":"https://orcid.org/0000-0002-3228-8067"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Maciej Tomczak","raw_affiliation_strings":["Sound and Music Analysis Group (SoMA), Digital Media Technology Lab (DMT Lab), School of Computing and Digital Technology, Birmingham City University, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3228-8067","affiliations":[{"raw_affiliation_string":"Sound and Music Analysis Group (SoMA), Digital Media Technology Lab (DMT Lab), School of Computing and Digital Technology, Birmingham City University, United Kingdom","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084229427","display_name":"Jason Hockman","orcid":"https://orcid.org/0000-0002-2911-6993"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jason Hockman","raw_affiliation_strings":["Sound and Music Analysis Group (SoMA), Digital Media Technology Lab (DMT Lab), School of Computing and Digital Technology, Birmingham City University, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2911-6993","affiliations":[{"raw_affiliation_string":"Sound and Music Analysis Group (SoMA), Digital Media Technology Lab (DMT Lab), School of Computing and Digital Technology, Birmingham City University, United Kingdom","institution_ids":["https://openalex.org/I12870472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056171040"],"corresponding_institution_ids":["https://openalex.org/I12870472"],"apc_list":null,"apc_paid":null,"fwci":0.1919,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44921077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"142"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9990000128746033,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7954181432723999},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7892504930496216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779515266418457},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7173972129821777},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5972780585289001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5467932224273682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5074478983879089},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5051353573799133},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4250108301639557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4018145799636841},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36513805389404297},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21476894617080688},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20348626375198364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07819059491157532}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7954181432723999},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7892504930496216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779515266418457},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7173972129821777},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5972780585289001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5467932224273682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5074478983879089},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5051353573799133},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4250108301639557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4018145799636841},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36513805389404297},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21476894617080688},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20348626375198364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07819059491157532},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3616195.3616206","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616195.3616206","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616206","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:e-space.mmu.ac.uk:632970","is_oa":true,"landing_page_url":"https://e-space.mmu.ac.uk/view/authors/0dd1c19d51a520c298190e299cc94cca.html>","pdf_url":"https://e-space.mmu.ac.uk/632970/1/3616195.3616206.pdf","source":{"id":"https://openalex.org/S4306401617","display_name":"e-space (Manchester Metropolitan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11983389","host_organization_name":"Manchester Metropolitan University","host_organization_lineage":["https://openalex.org/I11983389"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:www.open-access.bcu.ac.uk:15136","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.open-access.bcu.ac.uk/15136/1/3616195.3616206.pdf","source":{"id":"https://openalex.org/S4306402654","display_name":"BCU Open Access Repository (Birmingham City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12870472","host_organization_name":"Birmingham City University","host_organization_lineage":["https://openalex.org/I12870472"],"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 or Workshop Item"}],"best_oa_location":{"id":"doi:10.1145/3616195.3616206","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616195.3616206","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616195.3616206","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Audio Mostly Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1187872781","display_name":"Augmented Reality Musical Ensemble (ARME)","funder_award_id":"EP/V034987/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3642338098","display_name":null,"funder_award_id":"EP/V034987/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387543615.pdf"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1936750108","https://openalex.org/W2140304104","https://openalex.org/W2405656250","https://openalex.org/W3193341057","https://openalex.org/W4311090042"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Recent":[0],"work":[1],"in":[2,43,54],"note":[3,146],"onset":[4,91,119,147],"detection":[5,92,120],"has":[6],"centered":[7],"on":[8,121,132,178,185],"deep":[9],"learning":[10],"models":[11,89],"such":[12],"as":[13,41,52,129,131,172],"recurrent":[14,97],"neural":[15,19],"networks":[16,20,27],"(RNN),":[17],"convolutional":[18,26,98],"(CNN)":[21],"and":[22,96,105,153],"more":[23],"recently":[24],"temporal":[25,95],"(TCN),":[28],"which":[29,100],"achieve":[30],"high":[31],"evaluation":[32],"accuracies":[33],"for":[34,64,90,118],"onsets":[35,47,157],"characterized":[36],"by":[37,72],"clear,":[38],"well-defined":[39],"transients,":[40],"found":[42,53],"percussive":[44],"instruments.":[45,107],"However,":[46],"with":[48,145,158],"less":[49],"transient":[50],"presence,":[51],"string":[55,76,106,142,179],"instrument":[56,77,143],"recordings,":[57],"still":[58],"pose":[59],"a":[60,73,122,133,137],"relatively":[61],"difficult":[62],"challenge":[63,68],"state-of-the-art":[65,116,176],"algorithms.":[66],"This":[67],"is":[69],"further":[70],"exacerbated":[71],"paucity":[74],"of":[75,111,141,168,188],"data":[78],"containing":[79],"expert":[80],"annotations.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"propose":[86],"two":[87],"new":[88],"using":[93],"bidirectional":[94],"networks,":[99],"generalise":[101],"to":[102],"polyphonic":[103],"signals":[104],"We":[108],"perform":[109],"evaluations":[110],"the":[112,126,166,175],"proposed":[113,139],"methods":[114],"alongside":[115],"algorithms":[117,177],"benchmark":[123],"dataset":[124,140],"from":[125,136],"MIR":[127],"community,":[128],"well":[130],"test":[134],"set":[135],"newly":[138],"recordings":[144,180],"annotations,":[148],"comprising":[149],"approximately":[150],"40":[151],"minutes":[152],"over":[154],"8,000":[155],"annotated":[156],"varied":[159],"expressive":[160],"playing":[161],"styles.":[162],"The":[163],"results":[164],"demonstrate":[165],"effectiveness":[167],"both":[169],"presented":[170],"models,":[171],"they":[173],"outperform":[174],"while":[181],"maintaining":[182],"comparative":[183],"performance":[184],"other":[186],"types":[187],"music.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2025-10-10T00:00:00"}