Search papers, labs, and topics across Lattice.
3
1
2
7
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.
Dense-Sparse DTW can significantly improve the customization of piano accompaniments, outperforming complex methods while simplifying the alignment process.
