{"id":"https://openalex.org/W2534843682","doi":"https://doi.org/10.1109/iscslp.2016.7918477","title":"Speaker diarization system for autism children's real-life audio data","display_name":"Speaker diarization system for autism children's real-life audio data","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2534843682","doi":"https://doi.org/10.1109/iscslp.2016.7918477","mag":"2534843682"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210129003","display_name":"SYSU-CMU International Joint Research Institute","ror":"https://ror.org/02w30ae27","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129003"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["SYSU-CMU Joint Institute of Engineering, Sun Yat-sen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SYSU-CMU Joint Institute of Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I4210129003","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103888187","display_name":"Weicheng Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210129003","display_name":"SYSU-CMU International Joint Research Institute","ror":"https://ror.org/02w30ae27","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129003"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weicheng Cai","raw_affiliation_strings":["SYSU-CMU Joint Institute of Engineering, Sun Yat-sen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SYSU-CMU Joint Institute of Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I4210129003","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210146956","display_name":"Third Affiliated Hospital of Sun Yat-sen University","ror":"https://ror.org/04tm3k558","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210146956"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Chen","raw_affiliation_strings":["The Third Affiliated Hospital, Sun Yat-sen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Third Affiliated Hospital, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I4210146956","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102932949","display_name":"Xiaobing Zou","orcid":"https://orcid.org/0000-0002-7380-0979"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210146956","display_name":"Third Affiliated Hospital of Sun Yat-sen University","ror":"https://ror.org/04tm3k558","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210146956"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Zou","raw_affiliation_strings":["The Third Affiliated Hospital, Sun Yat-sen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Third Affiliated Hospital, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I4210146956","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032367559","display_name":"Shilei Zhang","orcid":"https://orcid.org/0000-0001-8169-0098"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["Speech Technology and Solution Group, IBM China Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Solution Group, IBM China Research Laboratory","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013165064","display_name":"Ming Li","orcid":"https://orcid.org/0000-0001-5173-1602"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210129003","display_name":"SYSU-CMU International Joint Research Institute","ror":"https://ror.org/02w30ae27","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129003"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["SYSU-CMU Joint Institute of Engineering, Sun Yat-sen University, China","SYSU-CMU Shunde International Joint Research Institute, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SYSU-CMU Joint Institute of Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I4210129003","https://openalex.org/I157773358"]},{"raw_affiliation_string":"SYSU-CMU Shunde International Joint Research Institute, China","institution_ids":["https://openalex.org/I4210129003","https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5105,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.65505717,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.707658052444458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7039353847503662},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6696412563323975},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.643692672252655},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5903839468955994},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47892507910728455},{"id":"https://openalex.org/keywords/autism","display_name":"Autism","score":0.45217397809028625},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44693148136138916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37434273958206177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35382649302482605},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.25541114807128906},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11111000180244446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707658052444458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7039353847503662},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6696412563323975},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.643692672252655},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5903839468955994},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47892507910728455},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.45217397809028625},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44693148136138916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37434273958206177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35382649302482605},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25541114807128906},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11111000180244446},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1504503307","https://openalex.org/W1563939609","https://openalex.org/W1587845029","https://openalex.org/W1608667326","https://openalex.org/W2038162002","https://openalex.org/W2044591814","https://openalex.org/W2081074144","https://openalex.org/W2082968463","https://openalex.org/W2110783210","https://openalex.org/W2127779539","https://openalex.org/W2138730338","https://openalex.org/W2140537255","https://openalex.org/W2144125830","https://openalex.org/W2152615462","https://openalex.org/W2159591770","https://openalex.org/W2405802804","https://openalex.org/W2407637315","https://openalex.org/W6628911050","https://openalex.org/W6635141280","https://openalex.org/W6636488977","https://openalex.org/W6676462321","https://openalex.org/W6678849049","https://openalex.org/W6713732491","https://openalex.org/W6713978812","https://openalex.org/W6738904159"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W4280602684","https://openalex.org/W2333799855","https://openalex.org/W4310092953","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W3200375535","https://openalex.org/W159467828"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,80,101,115],"introduce":[4],"several":[5],"methods":[6,154,174],"to":[7,35,104,126],"improve":[8],"the":[9,25,37,57,72,166,177],"performance":[10],"of":[11,86,182],"speaker":[12],"diarization":[13],"system":[14,22],"for":[15,28,111],"autism":[16],"children's":[17,38,106],"real-life":[18],"audio":[19,46],"data.":[20],"This":[21],"serves":[23],"as":[24],"frontend":[26],"module":[27],"further":[29,81,112],"speech":[30,39,107,113],"analysis.":[31],"Our":[32],"objective":[33],"is":[34],"detect":[36],"from":[40,123,162],"single":[41],"channel,":[42],"noisy":[43],"and":[44,94,186],"daily":[45],"recordings":[47],"collected":[48,161],"by":[49],"wearable":[50],"devices":[51],"in":[52,56,108,180],"real":[53],"environment.":[54],"First,":[55],"conventional":[58],"generalized":[59],"likelihood":[60],"ratio":[61],"(GLR)":[62],"distance":[63],"with":[64],"agglomerative":[65],"hierarchical":[66],"clustering":[67],"(AHC)":[68],"framework,":[69],"besides":[70],"using":[71,132],"line":[73],"spectral":[74],"pair":[75],"(LSP)":[76],"based":[77],"GLR":[78,88],"distance,":[79],"propose":[82],"a":[83,117,156],"weighted":[84],"summation":[85],"multiple":[87],"distances":[89],"combining":[90],"LSP,":[91],"pitch,":[92],"energy":[93],"phoneme":[95],"duration":[96],"information":[97],"together.":[98],"Second,":[99],"since":[100],"only":[102],"want":[103],"extract":[105],"high":[109],"purity":[110],"analysis,":[114],"utilize":[116],"30":[118],"seconds":[119],"long":[120],"enrollment":[121],"utterance":[122],"each":[124],"child":[125,129,183],"perform":[127],"supervised":[128,141],"cluster":[130,142],"selection":[131,143],"i-vector":[133],"cosine":[134],"distance.":[135],"We":[136,151],"find":[137],"out":[138],"that":[139,172],"performing":[140],"at":[144],"AHC":[145],"early":[146],"stages":[147],"generates":[148],"higher":[149],"purity.":[150],"evaluate":[152],"our":[153,173],"on":[155],"120":[157],"minutes":[158],"subset":[159],"data":[160],"three":[163],"children":[164],"during":[165],"child-therapist":[167],"interactions.":[168],"Experimental":[169],"results":[170],"show":[171],"significantly":[175],"outperform":[176],"GLR-AHC":[178],"baseline":[179],"terms":[181],"cluster's":[184],"recall":[185],"precision.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}