{"id":"https://openalex.org/W4372262450","doi":"https://doi.org/10.1109/icassp49357.2023.10094777","title":"Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation","display_name":"Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262450","doi":"https://doi.org/10.1109/icassp49357.2023.10094777"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100340161","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0002-3710-5979"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338131","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0003-1451-5251"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522530","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-5631-0639"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101014847","display_name":"Lu Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu Lu","raw_affiliation_strings":["Shanghai Media Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Media Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074843536","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0003-2436-5162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6629,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84468243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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":0.9998000264167786,"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":0.9987000226974487,"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/T10057","display_name":"Face and Expression Recognition","score":0.96670001745224,"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":0.7871055006980896},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6338433027267456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5960357189178467},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5879595279693604},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5546271204948425},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5126644968986511},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.49650079011917114},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4860982894897461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47734788060188293},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46168985962867737},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39597854018211365},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3273981809616089},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32389092445373535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1944074034690857},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09658020734786987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871055006980896},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6338433027267456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5960357189178467},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5879595279693604},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5546271204948425},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5126644968986511},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.49650079011917114},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4860982894897461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47734788060188293},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46168985962867737},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39597854018211365},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3273981809616089},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32389092445373535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1944074034690857},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09658020734786987},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W54230203","https://openalex.org/W116902681","https://openalex.org/W1922655562","https://openalex.org/W2486034530","https://openalex.org/W2806379360","https://openalex.org/W2889048668","https://openalex.org/W2902836694","https://openalex.org/W2945478979","https://openalex.org/W2963405869","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981263323","https://openalex.org/W3015654635","https://openalex.org/W3019952993","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3161294170","https://openalex.org/W3197216873","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3214444848","https://openalex.org/W4200630629","https://openalex.org/W4221145109","https://openalex.org/W4226132755","https://openalex.org/W4385823092","https://openalex.org/W6602235367","https://openalex.org/W6604828220","https://openalex.org/W6734312481","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2371334198","https://openalex.org/W4255510578","https://openalex.org/W1987584713","https://openalex.org/W2048360808","https://openalex.org/W2124026597","https://openalex.org/W4386197183","https://openalex.org/W4385451382","https://openalex.org/W2105210619","https://openalex.org/W2136499149","https://openalex.org/W2153462642"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,19,54,78,133],"face":[2,20,55,79,134],"has":[3],"attracted":[4],"broad":[5],"interest":[6],"from":[7],"academia":[8],"and":[9,15,23,94,115],"industry":[10],"recently.":[11],"However,":[12],"data":[13,28,46],"acquisition":[14],"labeling":[16],"in":[17,31,76],"audio-driven":[18],"are":[21,86],"labor-intensive":[22],"costly.":[24],"The":[25,57,102],"lack":[26],"of":[27,52,70,92,128],"resource":[29],"results":[30],"poor":[32],"synthesis":[33],"effect.":[34],"To":[35],"alleviate":[36],"this":[37],"issue,":[38],"we":[39],"propose":[40],"to":[41,48,88,96],"use":[42],"TTS":[43,63,137],"(Text-To-Speech)":[44],"for":[45,132],"augmentation":[47],"improve":[49],"few-shot":[50,130],"ability":[51],"the":[53,62,68,77,121,126],"system.":[56],"misalignment":[58],"problem":[59],"brought":[60],"by":[61,84],"audio":[64],"is":[65,73],"solved":[66],"with":[67,136],"introduction":[69],"soft-DTW,":[71],"which":[72,124],"first":[74],"adopted":[75],"task.":[80],"Moreover,":[81],"features":[82],"extracted":[83],"HuBERT":[85],"explored":[87],"utilize":[89],"underlying":[90],"information":[91],"audio,":[93],"found":[95],"be":[97],"superior":[98],"over":[99,120],"other":[100],"features.":[101],"proposed":[103],"method":[104],"achieves":[105],"17%,":[106],"14%,":[107],"38%":[108],"dominance":[109],"on":[110],"MSE":[111],"score,":[112],"DTW":[113],"score":[114],"user":[116],"study":[117],"preference":[118],"repectively":[119],"baseline":[122],"model,":[123],"shows":[125],"effectiveness":[127],"improving":[129],"learning":[131],"system":[135],"augmentation.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
