{"id":"https://openalex.org/W3183562410","doi":"https://doi.org/10.1145/3468784.3471604","title":"Real-time Sound Visualization via Multidimensional Clustering and Projections","display_name":"Real-time Sound Visualization via Multidimensional Clustering and Projections","publication_year":2021,"publication_date":"2021-06-29","ids":{"openalex":"https://openalex.org/W3183562410","doi":"https://doi.org/10.1145/3468784.3471604","mag":"3183562410"},"language":"en","primary_location":{"id":"doi:10.1145/3468784.3471604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468784.3471604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 12th International Conference on Advances in Information Technology","raw_type":"proceedings-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/A5101099413","display_name":"Nhat Le","orcid":null},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nhat Le","raw_affiliation_strings":["Texas Tech University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University, United States","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034489450","display_name":"Ngan Nguyen","orcid":"https://orcid.org/0000-0001-5039-8019"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ngan V.T. Nguyen","raw_affiliation_strings":["Texas Tech University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University, United States","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032280607","display_name":"Tommy Dang","orcid":"https://orcid.org/0000-0001-8322-0014"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tommy Dang","raw_affiliation_strings":["Texas Tech University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University, United States","institution_ids":["https://openalex.org/I12315562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08321617,"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":"1","last_page":"6"},"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":0.9958000183105469,"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":0.9937999844551086,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8337339162826538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8086338043212891},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.807768702507019},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5523411631584167},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5199617147445679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5129780173301697},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4717206358909607},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4428038001060486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37506765127182007},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.23695844411849976}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8337339162826538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086338043212891},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.807768702507019},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5523411631584167},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5199617147445679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5129780173301697},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4717206358909607},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4428038001060486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37506765127182007},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23695844411849976},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3468784.3471604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468784.3471604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 12th International Conference on Advances in Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W235499453","https://openalex.org/W2071913706","https://openalex.org/W2121647670","https://openalex.org/W2133824856","https://openalex.org/W2135415614","https://openalex.org/W2139435939","https://openalex.org/W2162676242","https://openalex.org/W2187089797","https://openalex.org/W2342317837"],"related_works":["https://openalex.org/W2013728941","https://openalex.org/W4225274103","https://openalex.org/W2579659702","https://openalex.org/W2154046714","https://openalex.org/W1965329638","https://openalex.org/W2189613078","https://openalex.org/W2923661510","https://openalex.org/W1574055964","https://openalex.org/W2542318691","https://openalex.org/W3160708108"],"abstract_inverted_index":{"Sound":[0,32],"plays":[1],"a":[2,48,93,142],"vital":[3],"role":[4],"in":[5,85,109,171],"every":[6],"aspect":[7],"of":[8,15,39,50,57,103,182],"human":[9,107,131],"life":[10],"since":[11],"it":[12],"is":[13,36,47,54,80,152],"one":[14],"the":[16,30,37,55,81,126,130,168,172],"primary":[17],"sensory":[18],"information":[19],"that":[20,45],"our":[21],"auditory":[22],"system":[23],"collects":[24],"and":[25,34,41,63,73,88,98,106,161],"allows":[26],"us":[27],"to":[28,65,71,96,124,165,176],"perceive":[29],"world.":[31],"clustering":[33,87,160,169],"visualization":[35,163],"process":[38,46],"collecting":[40],"analyzing":[42],"audio":[43,78],"samples;":[44],"prerequisite":[49],"sound":[51,86,101],"classification,":[52],"which":[53],"core":[56],"automatic":[58],"speech":[59,66,108],"recognition,":[60],"virtual":[61],"assistants,":[62],"text":[64],"applications.":[67],"Nevertheless,":[68],"understanding":[69],"how":[70],"recognize":[72],"properly":[74,166],"interpret":[75],"complex,":[76],"high-dimensional":[77,113,162],"data":[79,114,159],"most":[82,173],"significant":[83],"challenge":[84],"visualization.":[89],"This":[90,154],"paper":[91,155],"proposed":[92],"web-based":[94],"platform":[95],"visualize":[97],"cluster":[99],"similar":[100],"samples":[102],"musical":[104,183],"notes":[105,184],"real-time.":[110],"For":[111],"visualizing":[112],"like":[115],"audio,":[116],"Mel-Frequency":[117],"Cepstral":[118],"Coefficients":[119],"(MFCCs)":[120],"were":[121],"initially":[122],"developed":[123],"represent":[125],"sounds":[127],"made":[128],"by":[129,186],"vocal":[132],"tract":[133],"are":[134],"extracted.":[135],"Then,":[136],"t-distributed":[137],"Stochastic":[138],"Neighbor":[139],"Embedding":[140],"(t-SNE),":[141],"dimensionality":[143],"reduction":[144],"technique,":[145],"was":[146],"designed":[147],"for":[148],"high":[149],"dimensional":[150],"datasets":[151],"applied.":[153],"focuses":[156],"on":[157],"both":[158],"methods":[164],"present":[167],"results":[170],"meaningful":[174],"way":[175],"uncover":[177],"potentially":[178],"interesting":[179],"behavioral":[180],"patterns":[181],"played":[185],"different":[187],"instruments.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}