Compression of Acoustic Event Detection Models with Low-rank Matrix Factorization and Quantization Training
2019-05-02NIPS Workshop CDNNRIAUnverified0· sign in to hype
Bowen Shi, Ming Sun, Chieh-Chi Kao, Viktor Rozgic, Spyros Matsoukas, Chao Wang
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
In this paper, we present a compression approach based on the combination of low-rank matrix factorization and quantization training, to reduce complexity for neural network based acoustic event detection (AED) models. Our experimental results show this combined compression approach is very effective. For a three-layer long short-term memory (LSTM) based AED model, the original model size can be reduced to 1% with negligible loss of accuracy. Our approach enables the feasibility of deploying AED for resource-constraint applications.