Qian Chen

STAR-VAE achieves state-of-the-art audio reconstruction fidelity by aligning latent space geometry with the hierarchical structure of audio signals.

AudioCALM achieves state-of-the-art performance in speech, sound, and music generation by seamlessly integrating diverse audio modalities into a single autoregressive framework.

Achieving high-quality voice cloning without any intermediate representations could revolutionize text-to-speech synthesis.

Seamless transitions between speech and singing modes are now driven purely by text context, achieving state-of-the-art results in code-switching synthesis.

Standard multimodal fusion can hurt performance in emotion recognition, but this new approach knows when to drop modalities, leading to state-of-the-art results.