Search papers, labs, and topics across Lattice.
5
0
5
5
Environmental audio manipulation is easier to detect than synthetic speech, but existing detectors fail to handle both effectively, revealing critical gaps in current audio forensics.
Deterministic probability flows outperform stochastic diffusion in clustering accuracy, achieving new state-of-the-art results in incomplete multi-view scenarios.
Current LALMs exhibit significant performance disparities across cognitive auditory capabilities, revealing a critical oversight in existing evaluation methods.
LALMs struggle to remember non-speech sounds across multi-turn conversations not because of faulty attention, but because their internal representations of those sounds drift over time.
Achieve a 62.7% BLEU score boost in speech emotion captioning by offloading only the trickiest parts of the problem to the cloud.
