{"id":"https://openalex.org/W107443397","doi":"https://doi.org/10.21437/icslp.2002-212","title":"A sound source classification system based on subband processing","display_name":"A sound source classification system based on subband processing","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W107443397","doi":"https://doi.org/10.21437/icslp.2002-212","mag":"107443397"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-212","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5046810738","display_name":"Oytun T\u00fcrk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oytun Turk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064984043","display_name":"\u00d6mer \u015eayli\u0307","orcid":"https://orcid.org/0000-0001-9702-5287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omer Sayli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001721758","display_name":"Helin Duta\u011fac\u0131","orcid":"https://orcid.org/0000-0003-4528-9277"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helin Dutagaci","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017246112","display_name":"Levent M. Arslan","orcid":"https://orcid.org/0000-0002-6086-8018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levent M. Arslan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2893,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.43764622,"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":"641","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/speech-recognition","display_name":"Speech recognition","score":0.7628302574157715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7301602363586426},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6513808369636536},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6069396734237671},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.593460202217102},{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.5660471320152283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5009870529174805},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4754828214645386},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4687903821468353},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43952909111976624},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41318830847740173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37038150429725647},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.35229384899139404},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.32385921478271484},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08733376860618591}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7628302574157715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301602363586426},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6513808369636536},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6069396734237671},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.593460202217102},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.5660471320152283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5009870529174805},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4754828214645386},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4687903821468353},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43952909111976624},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41318830847740173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37038150429725647},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.35229384899139404},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.32385921478271484},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08733376860618591},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.2002-212","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.3562","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.3562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sestek.com.tr/oytun/pubs/SoundSourceRecognition_SPS2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.5583","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.5583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sestek.com.tr/oytun/pubs/SoundSourceRecognition_ICSLP2002.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1565658805","https://openalex.org/W1575829986","https://openalex.org/W1957105039","https://openalex.org/W2020792162","https://openalex.org/W2026980461","https://openalex.org/W2069501481","https://openalex.org/W2112620504","https://openalex.org/W2120132744","https://openalex.org/W2134185119","https://openalex.org/W2134383396","https://openalex.org/W2161605020","https://openalex.org/W2184354764","https://openalex.org/W2283867234","https://openalex.org/W3216284681","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W193702574","https://openalex.org/W2289868279","https://openalex.org/W1546240199","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W2109142991","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W2969585518"],"abstract_inverted_index":{"A":[0],"classification":[1,66,112,152],"system":[2,149],"that":[3,134,147],"aims":[4],"to":[5,46,61,84],"recognize":[6],"the":[7,34,48,65,76,86,92,97,103,114,148,155],"presence":[8],"of":[9,18,36,50,91,102,109,123,137],"sounds":[10,158],"from":[11,159],"different":[12,160],"sources":[13,161],"is":[14,31,117,128],"described.":[15],"The":[16,40,55,144],"type":[17],"audio":[19,53,98],"signals":[20],"considered":[21],"are":[22,68,106,162],"speech,":[23,139],"music,":[24,140],"noise":[25,141],"and":[26,58,78,88,111,142],"silence.":[27,143],"Appropriate":[28],"subband":[29],"processing":[30],"applied":[32],"for":[33],"characterization":[35],"each":[37],"sound":[38],"source.":[39],"algorithm":[41,116],"operates":[42],"in":[43,64,96],"four":[44],"steps":[45],"classify":[47],"contents":[49],"a":[51,132],"given":[52,104],"signal.":[54,99],"acoustical":[56,93,124],"parameters":[57,101],"statistical":[59],"measures":[60],"be":[62],"used":[63],"process":[67],"obtained":[69],"via":[70],"an":[71],"off-line":[72],"training":[73],"procedure.":[74],"In":[75],"silence":[77],"onset":[79],"detection":[80],"stages,":[81],"we":[82],"aim":[83],"label":[85],"starting":[87],"finishing":[89],"instants":[90],"events":[94],"present":[95],"Acoustical":[100],"signal":[105],"extracted,":[107],"analysis":[108],"variance":[110],"using":[113],"LBG":[115],"carried":[118],"out":[119,130],"by":[120],"generating":[121],"codebooks":[122],"vectors.":[125],"Experimental":[126],"work":[127],"carded":[129],"on":[131,154],"database":[133],"contains":[135],"mixtures":[136],"human":[138],"experiments":[145],"demonstrate":[146],"achieves":[150],"88%":[151],"success":[153],"average":[156],"when":[157],"presented":[163],"non-simultaneously.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}