The merging algorithm for an extraction of valid speech-sounds

Authors:
Jin Ok Kim;Han Wook Paek;Chin Hyun Chung;Wha Young Yim;Sang Hyo Lee
Affiliations:
School of Information and Communication Engineering, Sungkyunkwan University, Jangan-gu, Suwon, Kyunggi-do, Korea;Department of Information and Control Engineering, Kwangwoon University, Nowon-gu, Seoul, Korea;Department of Information and Control Engineering, Kwangwoon University, Nowon-gu, Seoul, Korea;Department of Information and Control Engineering, Kwangwoon University, Nowon-gu, Seoul, Korea;Department of Information and Control Engineering, Kwangwoon University, Nowon-gu, Seoul, Korea
Venue:
ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartII
Year:
2003

Citing 9
Cited 0

Fundamentals of speech recognition

Fundamentals of speech recognition
Essential wavelets for statistical applications and data analysis

Essential wavelets for statistical applications and data analysis
A practical handbook of speech coders

A practical handbook of speech coders
Digital Signal Processing: A Computer-Based Approach

Digital Signal Processing: A Computer-Based Approach
Speech and Audio Signal Processing: Processing and Perception of Speech and Music

Speech and Audio Signal Processing: Processing and Perception of Speech and Music
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Discrete Time Processing of Speech Signals

Discrete Time Processing of Speech Signals
Discrete-time speech signal processing: principles and practice

Discrete-time speech signal processing: principles and practice
De-noising by soft-thresholding

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

In general, high frequency noises included in a normal speech stream are difficult to remove from the speech stream. Because an unvoiced phoneme seems like a high frequency noise, it may be removed during denoising. A low frequency noise (hum noise), on the other hand, may come from a circuitry imbalance, a wrongly designed ground point in PCB, or imbalance among the parts mounted on a board. This experiment results show that the merging algorithm is very robust against external effects. The merging algorithm is proposed to extract valid speech-sounds in terms of position and frequency range. It needs some numerical methods for an adaptive DWT implementation and performs unvoiced/voiced classification and denoising. Since the merging algorithm can decide the processing parameters relating to voices only and is independent of system noises, it is useful for extracting valid speech-sounds. The merging algorithm has an adaptive feature for arbitrary system noises and an excellent denoising SNR (signal-to-noise ratio). Its extraction shows that the denoising of compounded noise and the improved extraction and the merging algorithm can not be disturbed by an unexpected system interference.