Search papers, labs, and topics across Lattice.
3
0
4
5
StreamTN is proposed, a lightweight LLM-based Chinese streaming TN model that employs a dual-track streaming framework in which input tokens and output tokens are processed on two parallel tracks, enabling low-latency real-time inference without complex prompting.
FlashTTS slashes First-Packet Latency to 325ms, revolutionizing real-time speech dialogue systems without sacrificing voice quality.
Open-source TTS models can beat commercial systems in specific languages, but current instruction-following TTS still struggles with complex instructions like nuanced paralinguistic controls.
