Deep sparse rectifier neural networks for speech denoising
Authors:
- 24 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Deep neural networks (DNNs) have been widely applied in speech recognition and enhancement. In this paper we present some experiments using deep rectifier neural networks for speech denoising. Rectified linear units (ReLUs) can make a sparse connection between hidden layers. We analyze the usage of regularization coefficient during training to encourage more sparseness. This method further improves the generalization ability of the DNN regression model in unseen noisy conditions. After pruning and retraining the sparse network, the computation and storage load can be largely reduced without degradation in performance, making it easier to deploy speech denoising DNNs on portable devices.Keywords
This publication has 16 references indexed in Scilit:
- Caffe2014
- A Regression Approach to Speech Enhancement Based on Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- A structure-preserving training target for supervised speech separation2014
- On rectified linear units for speech processing2013
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy SpeechIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Evaluation of Objective Quality Measures for Speech EnhancementIEEE Transactions on Audio, Speech, and Language Processing, 2007
- Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs2002
- Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systemsSpeech Communication, 1993