Search papers, labs, and topics across Lattice.
Xiamen University
3
0
3
MMAC reveals stark differences in audio captioning performance across multiple dimensions, challenging the adequacy of current evaluation methods.
SARA achieves a groundbreaking balance between high-fidelity audio and precise linguistic alignment, setting a new standard for zero-shot TTS systems.
HoliDubber revolutionizes video dubbing by seamlessly integrating speech and sound effects from a single text prompt, outperforming traditional methods in quality and synchronization.
