scholarly journals Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition

2019 ◽  
Author(s):  
Khoi-Nguyen C. Mac ◽  
Xiaodong Cui ◽  
Wei Zhang ◽  
Michael Picheny
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Large Scale ◽  
Deep Neural Network ◽  
Acoustic Modeling

scholarly journals Employing Robust Principal Component Analysis for Noise-Robust Speech Feature Extraction in Automatic Speech Recognition with the Structure of a Deep Neural Network

2018 ◽  
Vol 1 (3) ◽  
pp. 28 ◽  
Author(s):  
Jeih-weih Hung ◽  
Jung-Shan Lin ◽  
Po-Jen Wu
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Deep Neural Network ◽  
Principal Component ◽  
Component Analysis ◽  
Robust Principal Component Analysis ◽  
Speech Feature ◽  
Noise Robust

In recent decades, researchers have been focused on developing noise-robust methods in order to compensate for noise effects in automatic speech recognition (ASR) systems and enhance their performance. In this paper, we propose a feature-based noise-robust method that employs a novel data analysis technique—robust principal component analysis (RPCA). In the proposed scenario, RPCA is employed to process a noise-corrupted speech feature matrix, and the obtained sparse partition is shown to reveal speech-dominant characteristics. One apparent advantage of using RPCA for enhancing noise robustness is that no prior knowledge about the noise is required. The proposed RPCA-based method is evaluated with the Aurora-4 database and a task using a state-of-the-art deep neural network (DNN) architecture as the acoustic models. The evaluation results indicate that the newly proposed method can provide the original speech feature with significant recognition accuracy improvement, and can be cascaded with mean normalization (MN), mean and variance normalization (MVN), and relative spectral (RASTA)—three well-known and widely used feature robustness algorithms—to achieve better performance compared with the individual component method.

Sign in / Sign up

Export Citation Format

Share Document