Search papers, labs, and topics across Lattice.
3
0
6
8
SwanTale achieves unprecedented expressiveness in multi-speaker audio generation, outperforming existing models in both instruct and zero-shot tasks.
Adaptive cooling based on entropy feedback can drastically enhance the efficiency of deterministic MPPI control, achieving faster convergence without sacrificing robustness.
Current speech generation models still fall short in maintaining consistency and capturing nuanced expressiveness when generating long-form speech, despite advances in high-fidelity synthesis.
