{"id":"https://openalex.org/W2397059489","doi":"https://doi.org/10.1109/icassp.2016.7472739","title":"Low level descriptors based DBLSTM bottleneck feature for speech driven talking avatar","display_name":"Low level descriptors based DBLSTM bottleneck feature for speech driven talking avatar","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2397059489","doi":"https://doi.org/10.1109/icassp.2016.7472739","mag":"2397059489"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031508616","display_name":"Xinyu Lan","orcid":"https://orcid.org/0000-0002-2588-2877"},"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"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Xinyu Lan","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699660","display_name":"Li Xu","orcid":"https://orcid.org/0000-0003-2954-3271"},"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/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":"Xu Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072108648","display_name":"Yishuang Ning","orcid":null},"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/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":"Yishuang Ning","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","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/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"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"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/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/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","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/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"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"last","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"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lianhong Cai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen Key Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031508616"],"corresponding_institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2609,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80117899,"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":"5550","last_page":"5554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9945999979972839,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684421539306641},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.7456932663917542},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7307515144348145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7141039967536926},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6196072697639465},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5350433588027954},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48052534461021423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4613281786441803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4396416246891022},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43340060114860535},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.2603246569633484},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06639862060546875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684421539306641},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.7456932663917542},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7307515144348145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7141039967536926},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6196072697639465},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5350433588027954},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48052534461021423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4613281786441803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4396416246891022},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43340060114860535},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2603246569633484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06639862060546875},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W34110307","https://openalex.org/W36879466","https://openalex.org/W211912913","https://openalex.org/W219197677","https://openalex.org/W309418507","https://openalex.org/W950853366","https://openalex.org/W1501669607","https://openalex.org/W1569907127","https://openalex.org/W1674799117","https://openalex.org/W1985447466","https://openalex.org/W2012897754","https://openalex.org/W2047618352","https://openalex.org/W2064675550","https://openalex.org/W2074808018","https://openalex.org/W2078154198","https://openalex.org/W2135156782","https://openalex.org/W2142487393","https://openalex.org/W2144499799","https://openalex.org/W2157986450","https://openalex.org/W2163685610","https://openalex.org/W2168053878","https://openalex.org/W6601427873","https://openalex.org/W6601501743","https://openalex.org/W6608738965","https://openalex.org/W6610803811","https://openalex.org/W6630073874","https://openalex.org/W6637157234","https://openalex.org/W6681380790","https://openalex.org/W6684070144"],"related_works":["https://openalex.org/W3138471234","https://openalex.org/W4247958311","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W4396832849","https://openalex.org/W3013299381"],"abstract_inverted_index":{"Speech":[0],"is":[1],"bimodal":[2],"in":[3,64,68],"nature.":[4],"There":[5],"are":[6],"close":[7],"correlations":[8,91],"between":[9],"the":[10,15,51,56,73,79,133,149,157,163,178],"acoustic":[11,37,101],"speech":[12,28,65,82,166],"signals":[13],"and":[14,24,45,170],"visual":[16,47,87],"gestures":[17,48,88],"such":[18,119],"as":[19,132],"lip":[20,115],"movements,":[21],"facial":[22],"expressions":[23],"head":[25],"motions.":[26],"For":[27],"driven":[29,83,167],"talking":[30,84,168],"avatar,":[31,169],"how":[32],"to":[33,41,124],"derive":[34],"more":[35,43,171],"representative":[36],"features":[38,102,161],"from":[39],"which":[40,137],"predict":[42],"accurate":[44],"realistic":[46],"still":[49],"remains":[50],"research":[52],"problem.":[53],"Inspired":[54],"by":[55],"promising":[57],"performance":[58],"of":[59,75,81,97,165],"low":[60],"level":[61],"descriptors":[62],"(LLD)":[63],"emotion":[66],"recognition,":[67],"this":[69],"work,":[70],"we":[71,121],"investigate":[72],"usage":[74],"LLD":[76,140,151],"feature":[77,135,141,155],"for":[78,114,162],"task":[80,164],"avatar.":[85],"Furthermore,":[86],"also":[89,108,122],"demonstrate":[90],"with":[92,142],"not":[93],"only":[94],"context":[95],"information":[96,110,174],"past":[98],"or":[99],"future":[100],"(e.g.":[103,111],"anticipatory":[104],"co-articulation":[105],"phenomena)":[106],"but":[107],"textual":[109,112],"hints":[113],"movement).":[116],"To":[117],"incorporate":[118],"information,":[120],"propose":[123],"use":[125],"deep":[126],"bidirectional":[127],"long":[128],"short-term":[129],"memory":[130],"(DBLSTM)":[131],"bottleneck":[134,154],"extractor,":[136],"can":[138,175],"combine":[139],"contextual":[143,173],"information.":[144],"Experimental":[145],"results":[146],"indicate":[147],"that":[148],"proposed":[150],"based":[152],"DBLSTM":[153],"outperforms":[156],"conventional":[158],"spectrum":[159],"related":[160],"sophisticated":[172],"further":[176],"improve":[177],"performance.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}