{"id":"https://openalex.org/W2137384499","doi":"https://doi.org/10.1109/mulmm.2004.1264992","title":"A tonal features exploration algorithm with independent component analysis","display_name":"A tonal features exploration algorithm with independent component analysis","publication_year":2004,"publication_date":"2004-06-03","ids":{"openalex":"https://openalex.org/W2137384499","doi":"https://doi.org/10.1109/mulmm.2004.1264992","mag":"2137384499"},"language":"en","primary_location":{"id":"doi:10.1109/mulmm.2004.1264992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mulmm.2004.1264992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th International Multimedia Modelling Conference, 2004. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5042008682","display_name":"Hsin-Lung Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I98298690","display_name":"I-Shou University","ror":"https://ror.org/04d7e4m76","country_code":"TW","type":"education","lineage":["https://openalex.org/I98298690"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Lung Hsieh","raw_affiliation_strings":["Department of Information Engineering, I-Shou University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, I-Shou University, Taiwan","institution_ids":["https://openalex.org/I98298690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002917087","display_name":"Din-Yuen Chan","orcid":"https://orcid.org/0000-0001-5520-0817"},"institutions":[{"id":"https://openalex.org/I183570559","display_name":"National Chiayi University","ror":"https://ror.org/04gknbs13","country_code":"TW","type":"education","lineage":["https://openalex.org/I183570559"]},{"id":"https://openalex.org/I98298690","display_name":"I-Shou University","ror":"https://ror.org/04d7e4m76","country_code":"TW","type":"education","lineage":["https://openalex.org/I98298690"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Din-Yuen Chan","raw_affiliation_strings":["Department of Information Engineering, National Chiayi University, Chiayi, Taiwan","I-shou Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, National Chiayi University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I183570559"]},{"raw_affiliation_string":"I-shou Univ","institution_ids":["https://openalex.org/I98298690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11447","display_name":"Blind Source Separation Techniques","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":0.9904000163078308,"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/T11309","display_name":"Music and Audio Processing","score":0.9758999943733215,"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":0.7374527454376221},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6180893182754517},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5873607397079468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5151866674423218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151621103286743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49146902561187744},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4835505187511444},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4706774353981018},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4507182240486145},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.43787914514541626},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3100220263004303},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.25914764404296875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374527454376221},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6180893182754517},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5873607397079468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5151866674423218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151621103286743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49146902561187744},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4835505187511444},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4706774353981018},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4507182240486145},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.43787914514541626},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3100220263004303},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.25914764404296875},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mulmm.2004.1264992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mulmm.2004.1264992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th International Multimedia Modelling Conference, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1530838232","https://openalex.org/W1548802052","https://openalex.org/W2043843997","https://openalex.org/W2074188409","https://openalex.org/W2099741732","https://openalex.org/W2141224535","https://openalex.org/W2169850486","https://openalex.org/W4205778870"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W1519490734","https://openalex.org/W2610449869","https://openalex.org/W2990940109","https://openalex.org/W2164592009"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,26,37,42,50,58,65,71,87,96,101,110,117,121,128,140,145,150,155],"tonal":[4,39,55,72,80],"feature":[5],"exploration":[6],"(TFE)":[7],"algorithm":[8,35,147],"is":[9],"addressed":[10],"to":[11,13,24],"intent":[12],"explore":[14],"representative":[15,66],"audio":[16,52,88,132,152,158],"features,":[17],"which":[18],"can":[19,105,142,148],"offer":[20],"rather":[21],"discriminative":[22],"power":[23],"meet":[25],"classification":[27],"of":[28,32,61,123,130,139,157],"human":[29],"perception.":[30],"First":[31],"all,":[33],"TFE":[34,146],"searches":[36],"defined":[38],"tracks":[40,73],"from":[41,86],"successive":[43],"overlapped":[44],"frames":[45,67],"by":[46],"tracing":[47],"and":[48,93,136],"linking":[49],"near":[51],"tones.":[53],"The":[54,78,134],"track":[56],"plays":[57],"masking":[59],"role":[60],"specific":[62],"segments":[63],"where":[64],"are":[68,91,125],"fetched":[69],"along":[70],"based":[74],"on":[75,116],"their":[76],"significance.":[77],"unmasked":[79],"energies":[81],"for":[82,154],"different":[83],"subbands":[84],"resulting":[85],"psychoacoustic":[89],"module":[90],"aggregated":[92],"arranged":[94],"into":[95],"observation":[97,118],"data":[98],"matrix.":[99],"Finally,":[100],"signature":[102],"projection":[103],"matrix":[104,124],"be":[106],"learned":[107],"through":[108],"performing":[109],"independent":[111],"component":[112],"analysis":[113],"(ICA)":[114],"process":[115],"matrices":[119],"that":[120,144],"components":[122],"quantized":[126],"as":[127],"index":[129],"an":[131],"sequence.":[133],"precision":[135],"recall":[137],"rates":[138],"simulation":[141],"demonstrate":[143],"extract":[149],"concise":[151],"features":[153],"retrieval":[156],"content-based":[159],"database.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}