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 …

This paper presents the machine learning architecture of the Snips Voice Platform, a
software solution to perform Spoken Language Understanding on microprocessors typical of …

Recent advances in deep neural networks (DNNs) have substantially improved the accuracy
and speed of a variety of intelligent applications. Nevertheless, one obstacle is that DNN …

The present paper is Part 2 in this series of two papers. In Part 1 we provided an introduction
to Multiple Classifier Systems (MCS) with a focus into the fundamentals: basic nomenclature …

Recently, we made available WeNet, a production-oriented end-to-end speech recognition
toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address …

Once a popular theme of futuristic science fiction or far-fetched technology forecasts, digital
home assistants with a spoken language interface have become a ubiquitous commodity …

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 …

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 …

With the rapid development of Internet-of-Things (IoT) and the explosive advance of deep
learning, there is an urgent need to enable deep learning inference on IoT devices in Mobile …

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 …