Nanyang Technological University Model - Based Noise Robust Speech Recognition

Abstract

Noise robustness is a challenging problem when automatic speech recognition (ASR) system is deployed in real life applications. This report examines techniques to improve the robustness of ASR systems. Particularly, we focus on a group of model-based noise robust techniques, called vector Taylor series (VTS) method, that adapt the acoustic model of ASR… (More)

Topics

20 Figures and Tables

Cite this paper

@inproceedings{Duc2012NanyangTU, title={Nanyang Technological University Model - Based Noise Robust Speech Recognition}, author={Nguyen Duc and Hoang Ha and Haizhou Li}, year={2012} }