Michiel Bacchiani

TL;DR: In this article, the authors explore a variety of structural and optimization improvements to the Listen, Attend, and Spell (LAS) encoder-decoder architecture, which significantly improves performance.

TL;DR: The structure and application of an acoustic room simulator to generate large-scale simulated data for training deep neural networks for far-field speech recognition and performance is evaluated using a factored complex Fast Fourier Transform (CFFT) acoustic model introduced in earlier work.

TL;DR: This paper introduces a neural network architecture, which performs multichannel filtering in the first layer of the network, and shows that this network learns to be robust to varying target speaker direction of arrival, performing as well as a model that is given oracle knowledge of the true target Speaker direction.

TL;DR: This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the Framework.

TL;DR: The technical and system building advances made to the Google Home multichannel speech recognition system, which was launched in November 2016, result in a reduction of WER of 8-28% relative to the current production system.