Search papers, labs, and topics across Lattice.
5
0
7
4
Reinforcement learning outperforms supervised fine-tuning in adapting ASR systems to synthetic speech, achieving a 40% reduction in word error rates.
LLMs can judge speech recognition quality with near-human accuracy, blowing away traditional metrics like Word Error Rate.
Open-weight models can now generate realistic, long-form doctor-patient conversations with corresponding SOAP notes, providing a valuable resource for training and evaluating long-context audio reasoning systems.
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.
