Convolutional Neural Networks are a class of deep learning models designed to process grid-like data, such as images. They're particularly effective for tasks like image classification, object ...

Abstract: Discrete tokens provide compact and domain-adaptable representations of speech features. However, their application to disordered speech, characterized by articulation imprecision and ...

Triton kernels for causal depthwise separable convolutions with per-token (dynamic) convolution weights. The following example shows how to add low-rank dynamic short convolutions to the queries, keys ...