Search papers, labs, and topics across Lattice.
4
0
4
6
ChildVox reveals the current capabilities and limitations of audio and speech models in understanding the nuanced and developing acoustic world of children.
Training speaker diarization models solely on adult speech leads to surprisingly poor performance on children and older adults, but a simple multi-age training strategy can fix it.
Wearable sensors and speech AI can now unobtrusively reveal the hidden communication dynamics driving hospital caregiver workload and stress.
Existing speech naturalness predictors fall flat when judging multi-turn conversations, but a new dual-channel estimator closes the gap with human perception.
