Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
Eurohaptics
Past research has demonstrated that speech communication on the skin is entirely achievable. However, there is still no definitive conclusion on the best training method that minimizes the time it takes for users to reach a prescribed performance level with a speech communication device. The present study reports the design and testing of two learning approaches with a system that translates English phonemes to haptic stimulation patterns (haptic symbols). With the phoneme-based learning approach, users learned the haptic symbols associated with the phonemes before attempting to acquire words made up of the phonemes. With the word-based approach, users learned words on day one. Two experiments were conducted with the two learning approaches, each employing twelve participants who spent 100 minutes each learning 100 English words made up of 39 phonemes. Results in terms of the total number of words learned show that performance levels vary greatly among the individuals tested (with the best learners in both methods achieving word-recognition scores >90%-correct on a 100-word vocabulary), both approaches are feasible for successful acquisition of word through the skin, and the phoneme-based approach provides a more consistent path for learning across users in a shorter period of time.
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
Bilge Acun, Benjamin Lee, Fiodar Kazhamiaka, Kiwan Maeng, Manoj Chakkaravarthy, Udit Gupta, David Brooks, Carole-Jean Wu
Ilkan Esiyok, Pascal Berrang, Katriel Cohn-Gordon, Robert Künnemann