Robust Phoneme Recognizer at Noise Corrupted Acoustic Environment

Journal Title: Scholars Journal of Engineering and Technology - Year 2016, Vol 4, Issue 7

Abstract

This paper proposes a robust automatic phoneme recognizer for Japanese language in noise corrupted acoustic environments. From the previous studies it is found that some hidden factors such as speaking style, gender effects, and noisy acoustic environments degrade the performance of automatic phoneme recognizers (APRs). In this study, an APR is designed in noise corrupted acoustic environments resolving the noise effect. The proposed system comprises three stages. At first stage, a multilayer neural network (MLN) that outputs Distinctive Phonetic Features (DPFs) from the input acoustic features is incorporated, and then the Karhunen-Loeve Transformation (KLT) and the Gram-Schmidt (GS) algorithms are used at second stage to extract reduced feature vector. Finally, the output phoneme strings are generated by inserting the reduced features into a hidden Markov model (HMM) based classifier. It is observed from the experiments in clean and noisy acoustic environments that the proposed method provides higher recognition accuracy at lower Signal-to-Noise Ratios (SNRs).

Authors and Affiliations

Bulbul Ahamed, Rasel Ahmed, Khaled Mahmud, Mohammad NurulHuda

Keywords

Related Articles

Aerodynamics of Spinning Sphere in Ideal Flow

Abstract:Aerodynamic analysis is carried out using superimposition of uniform flow with doublet over a spinning sphere. Analytical solutions of the pressure distribution and lift force over the spinning sphere are obtain...

Flexible Electronics: Review and Status

Flexible electronics has undergone different innovations and its applications in different technology is overwhelming. High speed Computation; displays; energy generation; energy storage; flexible substrates; healthcare;...

A Video Compression Technique Based On Active Learning Approach

Many Video compression algorithms manipulate video frames to dramatically reduce the storage requirements and bandwidth required for transmission while maximizing perceived video quality. Typical video compression method...

The Design of Olap-Based Muti-Dimensional Analysis System for Hospital Information

A multi-dimensional analysis of the hospital information system design is proposed based on OLAP technology which realizes OLAP multi-dimensional data analysis. A number of themes are determined in accordance with the sp...

Discrete Event Simulation Business Process of Trading Companies

The medium discrete event simulation of business processes of the enterprise warehouse shopping package Any Logic was selected which provides the best tool for making management decisions. To create a simulation model of...

Download PDF file
  • EP ID EP385594
  • DOI -
  • Views 115
  • Downloads 0

How To Cite

Bulbul Ahamed, Rasel Ahmed, Khaled Mahmud, Mohammad NurulHuda (2016). Robust Phoneme Recognizer at Noise Corrupted Acoustic Environment. Scholars Journal of Engineering and Technology, 4(7), 308-311. https://europub.co.uk/articles/-A-385594