{"id":"https://openalex.org/W2538370046","doi":"https://doi.org/10.1109/iscslp.2016.7918453","title":"A multi-channel/multi-speaker interactive 3D audio-visual speech corpus in Mandarin","display_name":"A multi-channel/multi-speaker interactive 3D audio-visual speech corpus in Mandarin","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2538370046","doi":"https://doi.org/10.1109/iscslp.2016.7918453","mag":"2538370046"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918453","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/A5103813810","display_name":"Jun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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/I4210115303","display_name":"Synergy University","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]}],"countries":["CN","RU"],"is_corresponding":true,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","School of Information Science and Engineering, Lanzhou University, Lanzhou, China","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210120485","https://openalex.org/I19820366","https://openalex.org/I4210115303"]},{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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/I4210115303","display_name":"Synergy University","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":["Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210120485","https://openalex.org/I19820366","https://openalex.org/I4210115303"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104386582","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0002-9972-7597"},"institutions":[{"id":"https://openalex.org/I4210115303","display_name":"Synergy University","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210120485","https://openalex.org/I19820366","https://openalex.org/I4210115303"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100566854","display_name":"Wenpeng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"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/I4210115303","display_name":"Synergy University","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Wenpeng Zhou","raw_affiliation_strings":["Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210120485","https://openalex.org/I19820366","https://openalex.org/I4210115303"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103813810"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I19820366","https://openalex.org/I4210115303","https://openalex.org/I4210120485","https://openalex.org/I76214153"],"apc_list":null,"apc_paid":null,"fwci":0.5044,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65201858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"4","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":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/T10860","display_name":"Speech and Audio Processing","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/T11439","display_name":"Video Analysis and Summarization","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9941999912261963,"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":0.8430507183074951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7189693450927734},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6251062750816345},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6174817681312561},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5935729146003723},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.46871131658554077},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4607248604297638},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4502623677253723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4460229277610779},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41933929920196533},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39816784858703613},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3914756774902344},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.24987691640853882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430507183074951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7189693450927734},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6251062750816345},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6174817681312561},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5935729146003723},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.46871131658554077},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4607248604297638},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4502623677253723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4460229277610779},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41933929920196533},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39816784858703613},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3914756774902344},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.24987691640853882},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp.2016.7918453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918453","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"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/395688","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/395688","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article (CA)"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/422799","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/422799","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article (CA)"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W57796367","https://openalex.org/W1537011605","https://openalex.org/W1999098530","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2090551192","https://openalex.org/W2109647201","https://openalex.org/W2113814270","https://openalex.org/W2115406588","https://openalex.org/W2120974626","https://openalex.org/W2142518644","https://openalex.org/W2535438430"],"related_works":["https://openalex.org/W2170821097","https://openalex.org/W2205714567","https://openalex.org/W109284678","https://openalex.org/W4392932011","https://openalex.org/W4390897618","https://openalex.org/W2137058881","https://openalex.org/W2131711534","https://openalex.org/W4312668661","https://openalex.org/W2343205865","https://openalex.org/W2009814707"],"abstract_inverted_index":{"This":[0,23],"paper":[1,97],"presents":[2],"a":[3,56,88],"multi-channel/multi-speaker":[4],"3D":[5,58,72,130],"audio-visual":[6,131],"corpus":[7,24,126,132],"for":[8,98,133],"Mandarin":[9],"continuous":[10],"speech":[11,18,21],"recognition":[12],"and":[13,20,52,101,105,108],"other":[14],"fields,":[15],"such":[16],"as":[17,87],"visualization":[19],"synthesis.":[22],"consists":[25],"of":[26],"24":[27],"speakers":[28],"with":[29,63],"about":[30,33,116],"18k":[31],"utterances,":[32],"20":[34],"hours":[35],"in":[36,50,95],"total.":[37],"For":[38],"each":[39],"utterance,":[40],"the":[41,71,76,128],"audio":[42,100],"streams":[43,80],"were":[44,81],"recorded":[45],"by":[46,83],"two":[47],"professional":[48],"microphones":[49],"near-field":[51],"far-field":[53],"respectively,":[54],"while":[55],"marker-based":[57],"facial":[59],"motion":[60],"capturing":[61],"system":[62],"six":[64],"infrared":[65],"cameras":[66],"was":[67],"used":[68],"to":[69],"acquire":[70],"video":[73,79,102],"streams.":[74],"Besides,":[75],"corresponding":[77],"2D":[78],"captured":[82],"an":[84],"additional":[85],"camera":[86],"supplement.":[89],"A":[90],"data":[91,117],"process":[92,118],"is":[93,127],"described":[94],"this":[96,125],"synchronizing":[99],"streams,":[103],"detecting":[104],"correcting":[106],"outliers,":[107],"removing":[109],"head":[110],"motions":[111],"during":[112],"recording.":[113],"Finally,":[114],"results":[115],"are":[119],"also":[120],"discussed.":[121],"As":[122],"so":[123],"far,":[124],"largest":[129],"Mandarin.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
