The rapid uptake of mobile devices and the rising popularity of mobile applications and
services pose unprecedented demands on mobile and wireless networking infrastructure …

Recent years have witnessed an exponential increase in the use of mobile and embedded
devices. With the great success of deep learning in many fields, there is an emerging trend …

End-to-end (E2E) models, which directly predict output character sequences given input
speech, are good candidates for on-device speech recognition. E2E models, however …

Keyword spotting (KWS) is a critical component for enabling speech based user interactions
on smart devices. It requires real-time response and high accuracy for good user …

This work presents a scalable solution to open-vocabulary visual speech recognition. To
achieve this, we constructed the largest existing visual speech recognition dataset …

Contextual biasing to a specific domain, including a user's song names, app names and
contact names, is an important component of any production-level automatic speech …

The requirements for many applications of state-of-the-art speech recognition systems
include not only low word error rate (WER) but also low latency. Specifically, for many use …

In automatic speech recognition (ASR) what a user says depends on the particular context
she is in. Typically, this context is represented as a set of word n-grams. In this work, we …

We describe the design of our federated task processing system. Originally, the system was
created to support two specific federated tasks: evaluation and tuning of on-device ML …

In our age of ubiquitous digital displays, adults often read in short, opportunistic interludes.
In this context of Interlude Reading, we consider if manipulating font choice can improve …