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

An Efficient Design Method of News System

Using development method of dynamic and static B/S structure, this paper designed and implemented an static news system based on dynamic generation technology. The system overcomes the shortcomings of traditional dynamic...

Study on Chemical Treatments and Fabrication of Jute Fibre Reinforced Polyester (JFRP) Composites Suitable For Motorcycle Crash Helmet Production

The demand for natural fibers in polymer reinforcement has gained serious attention due to the fact that they are biodegradable and possess qualities similar to synthetic fibers. Chemical treatments have been successfull...

Power Grid Equipment Supplier Selection Based on Cloud Model and Hesitant Linguistic Information

Power grid equipment is the guarantee of the safe and stable operation of power grids, selecting rational power grid equipment suppliers is the focus of power grid enterprise. In order to select the equipment supplier fo...

Modern Cluster Integration of Advanced Weapon System and Wireless Sensor Based Combat System

Future combat system (FCS) is a network based soldier friendly system which connects eighteen individual weapon system connected with the soldier via network. The prime idea of FCS concept is to support the soldier with...

Design and FPGA Implementation of UART Using Microprogrammed Controller

This paper presents an implementation of Universal Asynchronous Receiver-Transmitter (UART) controller based on Microprogrammed Controller on Field Programmable Gate Array (FPGA. Our design of UART is fully functional an...

Download PDF file
  • EP ID EP385594
  • DOI -
  • Views 95
  • 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