Search papers, labs, and topics across Lattice.
3
0
7
1
Joint-Output On-Policy Distillation (JO-OPD) is proposed, which distills the model's stronger S2T policy into joint generation using student-generated S2TS trajectories, which reduces OMG across two interleaved generation architectures.
Semantic speech tokens can be refined to enhance intelligibility and consistency across speakers, with significant implications for voice conversion and TTS applications.
No single speech model excels at all editing tasks, revealing critical gaps in current Speech LLM capabilities.
