Recently, a number of approaches to train speech models by incorpo-ratin...
This paper introduces R-MelNet, a two-part autoregressive architecture w...
Musical expression requires control of both what notes are played, and h...
We demonstrate the use of conditional autoregressive generative models (...
We demonstrate a conditional autoregressive pipeline for efficient music...
Recent character and phoneme-based parametric TTS systems using deep lea...
We explore blindfold (question-only) baselines for Embodied Question
Ans...
Recent work has shown that collaborative filter-based recommender system...
We consider structure discovery of undirected graphical models from
obse...
In this paper, we propose a deep neural network architecture for object
...