Federated learning (FL) has experienced a boom in recent years, which is jointly promoted
by the prosperity of machine learning and Artificial Intelligence along with emerging privacy …

Deep Neural Networks (DNNs) are becoming an important tool in modern computing
applications. Accelerating their training is a major challenge and techniques range from …

Federated learning (FL) is a well established method for performing machine learning tasks
over massively distributed data. However in settings where data is distributed in a non-iid …

In distributed training of deep neural networks, parallel minibatch SGD is widely used to
speed up the training process by using multiple workers. It uses multiple workers to sample …

An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the
largest corpus which is suitable for conducting the speech recognition research and building …

This paper investigates replacing i-vectors for text-independent speaker verification with
embeddings extracted from a feedforward deep neural network. Long-term speaker …

Modern mobile devices have access to a wealth of data suitable for learning models, which
in turn can greatly improve the user experience on the device. For example, language …

In federated distributed learning, the goal is to optimize a global training objective defined
over distributed devices, where the data shard at each device is sampled from a possibly …

Abstract Training Deep Neural Networks is complicated by the fact that the distribution of
each layer's inputs changes during training, as the parameters of the previous layers …

We propose a practical approach based on federated learning to solve out-of-domain issues
with continuously running embedded speech-based models such as wake word detectors …