Search papers, labs, and topics across Lattice.
Univ Toulon, Aix Marseille Univ
2
0
3
Speech SSL works better without the baggage of discrete codebooks or EMA teachers: predicting raw latent states under Gaussian regularization outpaces existing sub-90M baselines by 43% on frozen ASR.
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.
