TADA Collection TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment | https://huggingface.co/papers/2602.23068 • 7 items • Updated Mar 24 • 71
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length Paper • 2512.04677 • Published Dec 4, 2025 • 177