184 citations · 557 across the 54 of their papers we have counts for
3 papers · 1 filter
On the efficient representation and execution of deep acoustic models
Raziel Alvarez, Rohit Prabhavalkar, Anton Bakhtin
In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit float…
On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition
Rohit Prabhavalkar, Ouais Alsharif, Antoine Bruguier +1
We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building…
Personalized Speech recognition on mobile devices
Ian McGraw, Rohit Prabhavalkar, Raziel Alvarez +8
We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-ti…