{"id":"https://openalex.org/W1983073502","doi":"https://doi.org/10.1109/iscslp.2014.6936604","title":"Automatic speech data clustering with human perception based weighted distance","display_name":"Automatic speech data clustering with human perception based weighted distance","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1983073502","doi":"https://doi.org/10.1109/iscslp.2014.6936604","mag":"1983073502"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th 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/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing","Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"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"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"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":"Jia Jia","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100969203","display_name":"Helen Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053661520","display_name":"Lianhong Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lianhong Cai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing","Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008726578","display_name":"Weifeng Li","orcid":"https://orcid.org/0000-0002-2105-3596"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Weifeng Li","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems, Tsinzhua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025119324"],"corresponding_institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089","https://openalex.org/I3131625388"],"apc_list":null,"apc_paid":null,"fwci":0.54426656,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65733514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983999729156494,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7256258726119995},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7041144371032715},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.621189534664154},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5930868983268738},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5906929969787598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48743370175361633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48049628734588623},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.4752785265445709},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42458999156951904},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4144285023212433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3585776388645172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256258726119995},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7041144371032715},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.621189534664154},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5930868983268738},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5906929969787598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48743370175361633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48049628734588623},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.4752785265445709},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42458999156951904},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4144285023212433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3585776388645172},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1517939602","https://openalex.org/W1559582325","https://openalex.org/W1585610988","https://openalex.org/W2026490135","https://openalex.org/W2027506564","https://openalex.org/W2097732741","https://openalex.org/W2104084893","https://openalex.org/W2120945046","https://openalex.org/W2156146072","https://openalex.org/W2407139314","https://openalex.org/W2496901602","https://openalex.org/W2916535084","https://openalex.org/W6630997582","https://openalex.org/W6633661684","https://openalex.org/W6635035540","https://openalex.org/W6677973343","https://openalex.org/W6713840630"],"related_works":["https://openalex.org/W2129888254","https://openalex.org/W2115336194","https://openalex.org/W1563946824","https://openalex.org/W2809929944","https://openalex.org/W2571943156","https://openalex.org/W2908630341","https://openalex.org/W4294624291","https://openalex.org/W2169159254","https://openalex.org/W4389080932","https://openalex.org/W126836336"],"abstract_inverted_index":{"Speech":[0],"data":[1,21,71,138],"from":[2],"internet":[3,136],"contain":[4],"different":[5,36,79,123,158],"speaking":[6,37,154],"styles":[7,38],"relating":[8],"to":[9,27,34,73,118,172],"information":[10],"genre,":[11],"emotions,":[12],"sentiments,":[13],"speaker":[14],"characters,":[15],"etc.":[16],"Automatic":[17],"classification":[18,134,197],"of":[19,56,61,95,122,135,142,146],"such":[20],"remains":[22],"a":[23,47,74,103,112],"challenging":[24],"problem":[25],"due":[26],"the":[28,32,42,64,70,93,120,132,143,153,174,187],"difficulty":[29],"in":[30,157,179,196],"defining":[31],"categories":[33],"characterize":[35],"clearly.":[39],"To":[40,101],"address":[41],"problem,":[43],"this":[44,108,130],"paper":[45,109],"proposes":[46,111],"method":[48,68,185],"based":[49,115],"on":[50,83,88,98,126,164],"x-means":[51,67],"clustering,":[52],"an":[53],"extended":[54],"version":[55],"k-means":[57],"without":[58],"fixed":[59],"number":[60],"classes,":[62],"for":[63],"task.":[65],"Moreover,":[66],"clusters":[69],"according":[72],"pre-defined":[75],"distance":[76,84,106,117,180,192],"measurement":[77,181],"considering":[78],"features.":[80],"Current":[81],"methods":[82],"measuring":[85],"only":[86],"focus":[87],"features":[89,97,125],"themselves":[90],"while":[91],"ignoring":[92],"impact":[94],"these":[96],"human":[99,113,127,147,175],"perception.":[100,128],"derive":[102],"more":[104],"reasonable":[105],"measurement,":[107],"also":[110],"perception":[114,148,176],"weighted":[116],"capture":[119,152],"contribution":[121],"acoustic":[124],"In":[129],"way,":[131],"automatic":[133],"speech":[137],"will":[139],"make":[140],"use":[141],"prior":[144,177],"knowledge":[145,178],"as":[149,151],"well":[150],"style":[155],"characteristics":[156],"datasets":[159],"with":[160,189,193],"varying":[161],"categories.":[162],"Experiments":[163],"listening":[165],"test":[166],"demonstrate":[167],"that":[168],"it":[169],"is":[170],"useful":[171],"introduce":[173],"and":[182],"our":[183],"proposed":[184],"outperforms":[186],"baseline":[188],"conventional":[190],"Euclidian":[191],"10%":[194],"improvement":[195],"accuracy.":[198]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
