Autonomous robots deployed in the real world will need control policies ...
We introduce the Universal Speech Model (USM), a single large model that...
We introduce Noise2Music, where a series of diffusion models is trained ...
Data augmentation is a ubiquitous technique used to provide robustness t...
We summarize the results of a host of efforts using giant automatic spee...
Knowledge Distillation is an effective method of transferring knowledge ...
The predictions of wide Bayesian neural networks are described by a Gaus...
We employ a combination of recent developments in semi-supervised learni...
Recently, a semi-supervised learning method known as "noisy student trai...
Recently, SpecAugment, an augmentation scheme for automatic speech
recog...
We investigate how the final parameters found by stochastic gradient des...
We present SpecAugment, a simple data augmentation method for speech
rec...