Search papers, labs, and topics across Lattice.
4
0
4
21
VoxAudio revolutionizes vocalized audio synthesis by embedding intelligible speech seamlessly within complex soundscapes, outperforming traditional methods that compromise on clarity and control.
Achieving high-quality audio reconstruction at unprecedented speeds, Qwen-Audio-VAE encodes 32 minutes of audio in just 541 ms.
Full-duplex dialogue systems are often mischaracterized, with many claiming capabilities they cannot deliver due to training limitations.
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.
