scholarly journals New continuous speech feature adjustment for a noise-robust CSR system

2011 ◽  
Author(s):  
Yiming Sun ◽  
Yoshikazu Miyanaga
Keyword(s):  
Continuous Speech ◽  
Speech Feature ◽  
Noise Robust

Research on the Continuous Speech Feature Extraction Method for Different Noise

2014 ◽  
Vol 513-517 ◽  
pp. 3589-3592
Author(s):  
Wei Liu ◽  
Yi Ming Sun ◽  
Yan Xiu Liu
Keyword(s):  
Recognition Rate ◽  
Noisy Environment ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Feature Extraction Method ◽  
Average Recognition Rate ◽  
Speech Feature ◽  
The Difference ◽  
Noise Robust ◽  
Speech Feature Extraction

We propose a noise-robust continuous speech recognition (CSR) method for modeling and recognition. In recognition, we divide the continuous speech vectors to segments using proposed algorithm, then use DRA based on the segments for recognition. The proposed method efficiency is studied for noisy environment. DRA decreases the difference between the model and recognition continuous speech vectors. The new algorithm focuses on adjust the vectors by using different maxima in different segments. Segment-based DRA algorithm can make noisy speech feature vectors closer to the model. The average recognition rate has been improved at different noise and SNR conditions.

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