Search papers, labs, and topics across Lattice.
4
0
4
5
You can reliably decode frustration from facial muscle activity, even when people aren't speaking aloud.
Control the accent of your TTS output without needing any accented training data, by transferring accent characteristics from other languages.
Achieve accent-specific speech synthesis without any accented training data by cleverly combining phonological rules with multilingual TTS.
A new multimodal dataset links brain activity, muscle activation, and articulation in speech, opening doors to understanding the causal chain of speech production.
