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
- EP ID EP385594
- DOI -
- Views 77
- Downloads 0
Study on Size Effect of GFRP Tube Concrete Steel Tube Composite Column under Axial Compression
FRP pipe concrete steel tube composite column (DSTC) is proposed by Professor TengJinguang, Hong Kong Polytech University, a new type of composite structure.In order to further study the axial compression performance of...
Online Framework based on Serious Games for Healthcare:Case Studies
Abstract: Integrating serious games for Health has been proposed through a unified framework expanding current Health informatics. Healthcare from this perspective includes care for persons with physical, mental or devel...
Prediction of Dustfall Generation over an Andisol and Entisol Soil and Negatife Impact To Human Health
Dustfall is one of the parameters of air pollution that can cause upper respiratory tract infections diseases. The objective of the research is to analyze the correlation between dustfall, soil moisture content, wind spe...
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...
Ranking of Stochastic DEA with using an integrated method using Data envelopment analysis and Fuzzy preference relations
An integrated method using data envelopment analysis and fuzzy preference relation model is one of the models in data envelopment analysis widely used by DEA people and practitioners. However, in many real applications,...