Suppressing aliasing noise in the speech feature domain for automatic speech recognition

Huiqun Deng; Douglas O’Shaughnessy

doi:10.1121/1.2918787

Suppressing aliasing noise in the speech feature domain for automatic speech recognition

The Journal of the Acoustical Society of America ◽

10.1121/1.2918787 ◽

2008 ◽

Vol 124 (1) ◽

pp. EL8-EL13

Author(s):

Huiqun Deng ◽

Douglas O’Shaughnessy

Keyword(s):

Speech Recognition ◽

Automatic Speech Recognition ◽

Speech Feature

Download Full-text

Coupling particle filters with automatic speech recognition for speech feature enhancement

10.21437/interspeech.2006-10 ◽

2006 ◽

Cited By ~ 6

Author(s):

Friedrich Faubel ◽

Matthias Wölfel

Keyword(s):

Speech Recognition ◽

Automatic Speech Recognition ◽

Particle Filters ◽

Feature Enhancement ◽

Speech Feature

Download Full-text

Speech Feature Evaluation for Bangla Automatic Speech Recognition

Technical Challenges and Design Issues in Bangla Language Processing ◽

10.4018/978-1-4666-3970-6.ch009 ◽

2013 ◽

pp. 169-208 ◽

Cited By ~ 1

Author(s):

Mohammed Rokibul Alam Kotwal ◽

Foyzul Hassan ◽

Mohammad Nurul Huda

Keyword(s):

Speech Recognition ◽

Automatic Speech Recognition ◽

Recognition Performance ◽

Dynamic Parameters ◽

Mel Frequency Cepstral Coefficients ◽

Phoneme Recognition ◽

Hybrid Features ◽

Feature Evaluation ◽

Speech Feature ◽

Speech Features

This chapter presents Bangla (widely known as Bengali) Automatic Speech Recognition (ASR) techniques by evaluating the different speech features, such as Mel Frequency Cepstral Coefficients (MFCCs), Local Features (LFs), phoneme probabilities extracted by time delay artificial neural networks of different architectures. Moreover, canonicalization of speech features is also performed for Gender-Independent (GI) ASR. In the canonicalization process, the authors have designed three classifiers by male, female, and GI speakers, and extracted the output probabilities from these classifiers for measuring the maximum. The maximization of output probabilities for each speech file provides higher correctness and accuracies for GI speech recognition. Besides, dynamic parameters (velocity and acceleration coefficients) are also used in the experiments for obtaining higher accuracy in phoneme recognition. From the experiments, it is also shown that dynamic parameters with hybrid features also increase the phoneme recognition performance in a certain extent. These parameters not only increase the accuracy of the ASR system, but also reduce the computation complexity of Hidden Markov Model (HMM)-based classifiers with fewer mixture components.

Download Full-text

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

Applied System Innovation ◽

10.3390/asi1030028 ◽

2018 ◽

Vol 1 (3) ◽

pp. 28 ◽

Cited By ~ 4

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.

Download Full-text