- Rohit Prabhavalkar
- Ouais Alsharif
- Antoine Bruguier
- Ian McGraw
Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE (2016)
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 compact and accurate speech recognition systems which can be run efficiently on mobile devices. In this work, we present a technique for general recurrent model compression that jointly compresses both recurrent and non-recurrent inter-layer weight matrices. We find that the proposed technique allows us to reduce the size of our Long Short-Term Memory (LSTM) acoustic model to a third of its original size with negligible loss in accuracy.
We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work