Search papers, labs, and topics across Lattice.
4
0
5
44
Achieving a 40% reduction in character error rate, this syllable-level UASR framework unlocks new potential for low-resource language recognition without costly phoneme resources.
Family-specific audio tagging can now achieve unprecedented accuracy in noisy, naturalistic environments, bridging the gap in infant-centered audio understanding.
LLMs can guide phoneme editing to create synthetic accented speech from just a handful of examples, substantially improving ASR accuracy where training data is scarce.
Overcome the scarcity of labeled data in dysarthric speech quality assessment with a novel data augmentation framework that leverages unlabeled data and outperforms state-of-the-art methods.
