Search papers, labs, and topics across Lattice.
3
0
4
4
Achieve single-pass alignment of multi-talker speech – a feat previously impossible – by modeling overlaps as shuffles.
LLMs can spot fake words in speech by recognizing common editing patterns, but this reliance on learned biases hinders generalization to new manipulation techniques.
Achieve zero-shot voice conversion competitive with methods requiring more data or training, using a simple, invertible linear method to disentangle speech content from speaker timbre.
