Humans encode information into sounds by controlling articulators and de...
Understanding the neural implementation of complex human behaviors is on...
To build speech processing methods that can handle speech as naturally a...
Articulatory representation learning is the fundamental research in mode...
Estimation of fundamental frequency (F0) in voiced segments of speech
si...
Generative deep neural networks are widely used for speech synthesis, bu...
Recent self-supervised learning (SSL) models have proven to learn rich
r...
In the articulatory synthesis task, speech is synthesized from input fea...
Decoding language representations directly from the brain can enable new...