Search papers, labs, and topics across Lattice.
3
0
5
48
Dataset-aware multitask learning can slash deepfake detection errors by over 13%, even without auxiliary annotations.
ProPS can generate speaker embeddings that accurately reflect complex attributes from simple natural language prompts, revolutionizing how we synthesize speaker identities.
Speech-aware LLMs are surprisingly bad at speaker verification, but a simple embedding injection trick closes the gap with dedicated systems while preserving the LLM's language abilities.
