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

Cryptanalysis of Arabic Poetry, ibn Tabataba Treatise

Cryptography has been practiced to conceal messages science antiquity by different civilizations, including the ancient Egyptian, Chinese, Indian, Mesopotamian, Greek and Roman. But in none of them was there any cryptana...

Empirical Evaluation of Major Items in the Treatment of Drilling Waste Water Fluid

Drilling fluid -mud - is usually composed by water, clay, weighing material and a few chemicals. The drilling fluids are applied extensively in the upstream oil and gas industry, and are critical to ensuring a safe and p...

Voice Activated Electronic Devices Control System For Home Appliances

Peripheral is the electronic equipment connected by cable to the CPU of a computer. Today the art of computer science lies in connecting computers with peripherals. In many circumstances, it looks more like magic than ar...

Effects on Testis of Human Being with Specific Absorption Rate (SAR) of Mobile Phone

Mobile phone radiations are harmful for all living things in the world. Different mobile handsets have different SAR. We have done theoretical study to find harm full effects on testis of human being. In this work the e...

Calibration pipe friction coefficient for oilfield water injection system based on the adjustable parameter tree

The oilfield water injection network had the characteristic which was the value of pipe roughness general between 0.013 and 0.018, so the method of adjustable parameter tree is proposed to calibration pipe friction coeff...

Download PDF file
  • EP ID EP385594
  • DOI -
  • Views 105
  • 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