Speech neuroprostheses have the potential to restore communication to people living with
paralysis, but naturalistic speed and expressivity are elusive. Here we use high-density …

Loss of speech after paralysis is devastating, but circumventing motor-pathway injury by
directly decoding speech from intact cortical activity has the potential to restore natural …

In this paper, we study articulatory synthesis, a speech synthesis method using human vocal
tract information that offers a way to develop efficient, generalizable and interpretable …

Understanding the neural implementation of complex human behaviors is one of the major
goals in neuroscience. To this end, it is crucial to find a true representation of the neural …

Audio deepfake detection (ADD) is crucial to combat the misuse of speech synthesized from
generative AI models. Existing ADD models suffer from generalization issues, with a large …

The performance of deep learning models depends significantly on their capacity to encode
input features efficiently and decode them into meaningful outputs. Better input and output …

Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a
new era of spoken language processing. Yet, the discovered units often remain in phonetic …

Accurate modeling of the vocal tract is necessary to construct articulatory representations for
interpretable speech processing and linguistics. However, vocal tract modeling is …

Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a
new era of spoken language processing. Yet, the discovered units often remain in phonetic …

Self-Supervised Learning (SSL) based models of speech have shown remarkable
performance on a range of downstream tasks. These state-of-the-art models have remained …