Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong, Shenzhen
3
0
3
FlexiSLM can operate at frame rates as low as 4.0 Hz while maintaining high-quality speech, effectively halving inference time compared to traditional models.
Speaker Anonymization enables real-time voice conversion without the latency penalties of future context buffering, revolutionizing streaming applications.
Random reshuffling mirror descent, previously unanalyzable for constrained nonconvex relative smooth problems, now has proven complexity bounds thanks to a novel dual kernel conditioning regularity condition.
