Deep Neural Network Approach for Single Channel Speech Enhancement Processing

Description
Title: Deep Neural Network Approach for Single Channel Speech Enhancement Processing
Authors: Li, Dongfu
Date: 2016
Abstract: Speech intelligibility represents how comprehensible a speech is. It is more important than speech quality in some applications. Single channel speech intelligibility enhancement is much more difficult than multi-channel intelligibility enhancement. It has recently been reported that training-based single channel speech intelligibility enhancement algorithms perform better than Signal to Noise Ratio (SNR) based algorithm. In this thesis, a training-based Deep Neural Network (DNN) is used to improve single channel speech intelligibility. To increase the performance of the DNN, the Multi-Resolution Cochlea Gram (MRCG) feature set is used as the input of the DNN. MATLAB objective test results show that the MRCG-DNN approach is more robust than a Gaussian Mixture Model (GMM) approach. The MRCG-DNN also works better than other DNN training algorithms. Various conditions such as different speakers, different noise conditions and reverberation were tested in the thesis.
URL: http://hdl.handle.net/10393/34472
http://dx.doi.org/10.20381/ruor-5532
CollectionThèses, 2011 - // Theses, 2011 -
Files