{"id":"https://openalex.org/W3187100396","doi":"https://doi.org/10.1109/icaiic57133.2023.10066992","title":"Deep Single Shot Musical Instrument Identification using Scalograms","display_name":"Deep Single Shot Musical Instrument Identification using Scalograms","publication_year":2023,"publication_date":"2023-02-20","ids":{"openalex":"https://openalex.org/W3187100396","doi":"https://doi.org/10.1109/icaiic57133.2023.10066992","mag":"3187100396"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic57133.2023.10066992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic57133.2023.10066992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"},"type":"preprint","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/A5059932291","display_name":"Debdutta Chatterjee","orcid":null},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Debdutta Chatterjee","raw_affiliation_strings":["National Institute Of Technology,Department of Electronics and communication Engineering,Durgapur,India,713209"],"affiliations":[{"raw_affiliation_string":"National Institute Of Technology,Department of Electronics and communication Engineering,Durgapur,India,713209","institution_ids":["https://openalex.org/I155837530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895455","display_name":"Arindam Dutta","orcid":"https://orcid.org/0000-0002-6234-4111"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arindam Dutta","raw_affiliation_strings":["Indian Institute of Science,Department of Computational and Data Sciences,Bangalore,India","Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computational and Data Sciences,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007896517","display_name":"Dibakar Sil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dibakar Sil","raw_affiliation_strings":["Steradian Semiconductors Pvt. Ltd.,Bangalore,India","Steradian Semiconductors Pvt. Ltd., Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Steradian Semiconductors Pvt. Ltd.,Bangalore,India","institution_ids":[]},{"raw_affiliation_string":"Steradian Semiconductors Pvt. Ltd., Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067032127","display_name":"Aniruddha Chandra","orcid":"https://orcid.org/0000-0002-9247-9009"},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aniruddha Chandra","raw_affiliation_strings":["National Institute Of Technology,Department of Electronics and communication Engineering,Durgapur,India,713209"],"affiliations":[{"raw_affiliation_string":"National Institute Of Technology,Department of Electronics and communication Engineering,Durgapur,India,713209","institution_ids":["https://openalex.org/I155837530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059932291"],"corresponding_institution_ids":["https://openalex.org/I155837530"],"apc_list":null,"apc_paid":null,"fwci":0.5912,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61341003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"389"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9926999807357788,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9854000210762024,"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":0.772735059261322},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.6804167032241821},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6713634729385376},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.649484395980835},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5654285550117493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5519161820411682},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5169562697410583},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4650481939315796},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4511418342590332},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44881078600883484},{"id":"https://openalex.org/keywords/musical-tone","display_name":"Musical tone","score":0.4313638210296631},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.42465639114379883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3824470639228821},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34119248390197754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08443218469619751},{"id":"https://openalex.org/keywords/pitch","display_name":"Pitch (Music)","score":0.06715172529220581}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772735059261322},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.6804167032241821},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6713634729385376},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.649484395980835},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5654285550117493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519161820411682},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5169562697410583},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4650481939315796},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4511418342590332},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44881078600883484},{"id":"https://openalex.org/C86011254","wikidata":"https://www.wikidata.org/wiki/Q2717062","display_name":"Musical tone","level":4,"score":0.4313638210296631},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.42465639114379883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3824470639228821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34119248390197754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08443218469619751},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.06715172529220581},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icaiic57133.2023.10066992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic57133.2023.10066992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"},{"id":"pmh:oai::81514","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1483217829","https://openalex.org/W2095705004","https://openalex.org/W2194775991","https://openalex.org/W2410860376","https://openalex.org/W2796101164","https://openalex.org/W2903502793","https://openalex.org/W2911484868","https://openalex.org/W3031572743","https://openalex.org/W3098670224","https://openalex.org/W6629031165","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W4385640522","https://openalex.org/W3135448569","https://openalex.org/W4230165289","https://openalex.org/W2006608756","https://openalex.org/W2917692242","https://openalex.org/W2045667453","https://openalex.org/W2047833876","https://openalex.org/W4318973113","https://openalex.org/W2402674073","https://openalex.org/W1973568112"],"abstract_inverted_index":{"Musical":[0],"instrument":[1],"identification":[2],"has":[3],"for":[4,108,132,146],"long":[5],"had":[6],"a":[7,33,54,82,87],"reputation":[8],"of":[9,12,20,58,90,102,124],"being":[10],"one":[11,73],"the":[13,18,31,37,42,59,66,91,99,147],"most":[14],"ill-posed":[15],"problems":[16],"in":[17],"field":[19],"musical":[21,95],"information":[22],"retrieval.":[23],"Despite":[24],"several":[25],"robust":[26],"attempts":[27],"made":[28],"at":[29],"solving":[30],"problem,":[32,61],"timeline":[34],"spanning":[35],"over":[36,117],"last":[38],"five":[39],"odd":[40],"decades,":[41],"problem":[43,67],"remains":[44],"an":[45],"open":[46],"conundrum.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,62],"take":[52],"on":[53,98],"further":[55],"complex":[56],"version":[57],"traditional":[60],"attempt":[63],"to":[64,80,93],"solve":[65],"with":[68,120],"minimal":[69],"data":[70],"available":[71,111],"-":[72],"audio":[74,104],"excerpt":[75],"per":[76],"class.":[77,150],"We":[78],"propose":[79],"use":[81],"convolutional":[83],"Siamese":[84],"network":[85],"and":[86,139],"residual":[88],"variant":[89],"same":[92],"identify":[94],"instruments":[96],"based":[97],"corresponding":[100],"scalograms":[101],"their":[103],"excerpts.":[105],"Results":[106],"obtained":[107],"two":[109],"publicly":[110],"datasets":[112],"validate":[113],"our":[114,128],"algorithm,":[115],"achieving":[116],"80%":[118],"accuracy":[119],"only":[121],"5":[122],"sets":[123],"training":[125],"data.":[126],"Moreover,":[127],"proposed":[129],"architectures":[130],"work":[131],"both":[133],"spectrograms":[134],"as":[135,137],"well":[136],"scalograms,":[138],"exhibit":[140],"improvements,":[141],"albeit":[142],"marginal":[143],"(\u2243":[144],"3%),":[145],"later":[148],"input":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
