Search papers, labs, and topics across Lattice.
5
1
6
39
A training-free self-embedding strategy can significantly enhance the detection of partial deepfake speech, even when only small segments are manipulated.
Embedding a neural codec representation enables full recovery of manipulated audio segments, a breakthrough for content integrity in speech recordings.
DAIEN-TTS achieves unprecedented control over speech synthesis by disentangling speaker characteristics from environmental factors, resulting in highly natural and contextually relevant audio outputs.
SpeechAgent-R's ability to adaptively coordinate skills and tools leads to a remarkable 15-point performance boost in complex audio reasoning tasks.
RL fine-tuning with GRPO can significantly boost the generalization of speech deepfake detectors to unseen attacks, outperforming standard supervised methods.
