{"id":"https://openalex.org/W2046345433","doi":"https://doi.org/10.1109/iscslp.2012.6423476","title":"Perceptual similarity between audio clips and feature selection for its measurement","display_name":"Perceptual similarity between audio clips and feature selection for its measurement","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2046345433","doi":"https://doi.org/10.1109/iscslp.2012.6423476","mag":"2046345433"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5001097432","display_name":"Qinghua Wu","orcid":"https://orcid.org/0000-0002-5981-2906"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Wu","raw_affiliation_strings":["Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450111","display_name":"Xiaolei Zhang","orcid":"https://orcid.org/0000-0002-6431-0169"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Zhang","raw_affiliation_strings":["Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100828802","display_name":"Ping Lv","orcid":"https://orcid.org/0000-0001-6095-3397"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Lv","raw_affiliation_strings":["Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014958566","display_name":"Ji Wu","orcid":"https://orcid.org/0000-0001-6170-726X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wu","raw_affiliation_strings":["Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Laboratory, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Multimedia Signal and Intelligent Information Processing Lab, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2477,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54923164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9947999715805054,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9818999767303467,"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":0.8004871606826782},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.699091911315918},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6931302547454834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6291900873184204},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5537942051887512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5482414960861206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5312459468841553},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5031353831291199},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4712790846824646},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4276343286037445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004871606826782},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.699091911315918},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6931302547454834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6291900873184204},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5537942051887512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5482414960861206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5312459468841553},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5031353831291199},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4712790846824646},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4276343286037445},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1519698338","https://openalex.org/W1989771497","https://openalex.org/W2008765103","https://openalex.org/W2059020775","https://openalex.org/W2090861223","https://openalex.org/W2101004273","https://openalex.org/W2104862701","https://openalex.org/W2106055371","https://openalex.org/W2110962145","https://openalex.org/W2147069236","https://openalex.org/W2149077290","https://openalex.org/W2153331925","https://openalex.org/W2317104543","https://openalex.org/W3021908862","https://openalex.org/W6604987197","https://openalex.org/W6682222477"],"related_works":["https://openalex.org/W2038216521","https://openalex.org/W2736574136","https://openalex.org/W2565286512","https://openalex.org/W2399955410","https://openalex.org/W3126677997","https://openalex.org/W2933782699","https://openalex.org/W2097377227","https://openalex.org/W4317383455","https://openalex.org/W2565238693","https://openalex.org/W3129283347"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,64],"explore":[4],"the":[5,47,61,92,99,106,116],"retrieval":[6,22],"of":[7,41,73,102,108,119],"perceptually":[8],"similar":[9],"audio.":[10],"It":[11],"focuses":[12],"on":[13],"finding":[14],"sounds":[15],"according":[16],"to":[17,33,45,60,66],"human":[18],"perceptions.":[19],"Thus":[20],"such":[21],"is":[23],"more":[24],"\u201chuman-centered\u201d":[25],"[1]":[26],"than":[27],"previous":[28],"audio":[29],"retrievals":[30],"which":[31],"intend":[32],"find":[34,67],"homologous":[35],"sounds.":[36],"We":[37],"make":[38],"comprehensive":[39],"use":[40],"various":[42],"acoustic":[43,52,74,96,122],"features":[44,53,75,103],"measure":[46],"perceptual":[48],"similarity.":[49],"Since":[50],"some":[51],"may":[54],"be":[55],"redundant":[56],"or":[57],"even":[58],"adverse":[59],"similarity":[62,109],"measurement,":[63],"propose":[65],"a":[68,120],"complementary":[69],"and":[70,89],"effective":[71,95],"combination":[72,101],"via":[76],"SFFS":[77],"(Sequential":[78],"Floating":[79],"Forward":[80],"Selection)":[81],"method.":[82],"Experimental":[83],"results":[84],"show":[85],"that":[86],"LSP,":[87],"MFCC,":[88],"PLP":[90],"are":[91],"three":[93],"most":[94],"features.":[97],"Moreover,":[98],"optimal":[100],"can":[104],"improve":[105],"accuracy":[107],"classification":[110],"by":[111],"about":[112],"2%":[113],"compared":[114],"with":[115],"best":[117],"performance":[118],"single":[121],"feature.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}