Search papers, labs, and topics across Lattice.
Fudan University, MOSI Intelligence
3
0
4
Fine-grained cross-modal alignment in audio-video generation can dramatically enhance synchronization and quality, as shown by OmniVAE's innovative training approach.
Achieve controllable and scalable speech generation with MOSS-TTS, enabling zero-shot voice cloning and long-form synthesis.
A purely Transformer-based audio tokenizer, pre-trained on 3M hours of data, leapfrogs existing codecs and even enables a fully autoregressive TTS model to outperform cascaded systems.
