Dataset Groups Activity Stream TalkSHOW A high-quality audiovisual dataset for speech-to-motion generation, consisting of 3D holistic body meshes and synchronized speech. BibTex: @dataset{Hongwei_Yi_and_Hualin_Liang_and_Yifei_Liu_and_Qiong_Cao_and_Yandong_Wen_and_Timo_Bolkart_and_Dacheng_Tao_and_Michael_J_Black_2024, abstract = {A high-quality audiovisual dataset for speech-to-motion generation, consisting of 3D holistic body meshes and synchronized speech.}, author = {Hongwei Yi and Hualin Liang and Yifei Liu and Qiong Cao and Yandong Wen and Timo Bolkart and Dacheng Tao and Michael J Black}, doi = {10.57702/2u16hwzs}, institution = {No Organization}, keyword = {'3D body meshes', 'co-speech gesture', 'gesture generation', 'speech-to-motion generation', 'synchronized speech'}, month = {dec}, publisher = {TIB}, title = {TalkSHOW}, url = {https://service.tib.eu/ldmservice/dataset/talkshow}, year = {2024} }
