Search papers, labs, and topics across Lattice.
3
0
5
5
Semantically enriched speech representations in FireRedTTS3 lead to unprecedented stability and fidelity in voice cloning and editing tasks.
Flow-matching transformers with latent multi-modal conditioning and self-reference can leapfrog existing virtual try-on methods in both visual fidelity and inference speed.
A single system now rivals or beats specialized models across ASR, voice activity detection, language ID, and punctuation, setting a new bar for industrial-grade speech processing.
