Different from previous work, CaSPR learns representations thatsupport spacetime continuity,arerobusttovariable andirregularly spacetime-sampled point clouds, and generalize to unseen object instances. Our approach divides the problem into two subtasks.

Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems.

Kernel methods augmented with random features give scalable algorithms for learning from big data.

In particular, V oicebox outperforms the state-of-the-art zero-shot TTS model V ALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster.