Search papers, labs, and topics across Lattice.
5
0
8
5
Reinforcement learning outperforms supervised fine-tuning in adapting ASR systems to synthetic speech, achieving a 40% reduction in word error rates.
Geometric Latent Reasoning reduces the length of reasoning chains in LLMs, achieving correct answers with fewer steps by leveraging continuous trajectories in embedding space.
LLMs can judge speech recognition quality with near-human accuracy, blowing away traditional metrics like Word Error Rate.
Just 4 hours of speech data closes the modality gap in LLM-based ASR, rivaling full-dataset fine-tuning and unlocking effective domain adaptation.
LLM-based ASR can get a context boost without the compute cost: compress prior audio turns into learned latent tokens and retain transcripts to recover accuracy while shrinking the audio footprint.
