Recurrent Neural Networks for Noise Reduction in Robust ASR.

AUTHORED BY
Andrew L Maas
Quoc V. Le
Tyler M. O'Neil
Oriol Vinyals
Patrick Nguyen
Andrew Y. Ng

Abstract

Recent work on deep neural networks as acoustic models for automatic speech recognition (ASR) have demonstrated substantial performance improvements. We introduce a model which uses a deep recurrent auto encoder neural network to denoise input features for robust ASR. The model is trained on stereo (noisy and clean) audio features to predict clean features given noisy input. The model makes no assumptions about how noise affects the signal, nor the existence of distinct noise environments. Instead, the model can learn to model any type of distortion or additive noise given sufficient training data. We demonstrate the model is competitive with existing feature denoising approaches on the Aurora2 task, and outperforms a tandem approach where deep networks are used to predict phoneme posteriors directly.

Download PDF

Related Projects

Leave a Reply

You must be logged in to post a comment