Digital Signal Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Degradation Reduction of Speech Signals


Affiliations
1 Department of Electronics and Electrical Communications, Faculty of Electronic Engineering. Menoufia University, Menouf, 32952, Egypt
2 Department of Electronics and Electrical Communications, Faculty of Electronic Engineering. Menoufia University, Menouf, 32952, Egypt
3 Department of Electronics and Electrical Communications, Menoufia University, Menouf, 32952, Egypt
     

   Subscribe/Renew Journal


Speech signal is a signal that conveys information about the identity, words, age and emotional state of the speaker. If this signal is corrupted by noise, this information may be lost or become difficult to hear.There are several speech enhancement methods such as spectral subtraction method, Wiener filter method and adaptive wiener filtering method. A proposed method of speech enhancement to reduce the degradation of speech signal is introduced in this paper depending on speech averaging, median filtering or minimum periodogram. This averaging method can be used as a preprocessing step in speaker identification. Simulation results show a good performance of the proposed speech enhancement method.

Keywords

Speech Recognition, Speech Enhancement, Speech Averaging, Spectral Subtraction,Wiener Filter, Adaptive Wiener Filter, Speech Quality Metrics.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 160

PDF Views: 1




  • Degradation Reduction of Speech Signals

Abstract Views: 160  |  PDF Views: 1

Authors

S. Abd El-Moneim
Department of Electronics and Electrical Communications, Faculty of Electronic Engineering. Menoufia University, Menouf, 32952, Egypt
M. A. Nassar
Department of Electronics and Electrical Communications, Faculty of Electronic Engineering. Menoufia University, Menouf, 32952, Egypt
M. Abdelnaby
Department of Electronics and Electrical Communications, Faculty of Electronic Engineering. Menoufia University, Menouf, 32952, Egypt
F. E. Abd El-Samie
Department of Electronics and Electrical Communications, Menoufia University, Menouf, 32952, Egypt

Abstract


Speech signal is a signal that conveys information about the identity, words, age and emotional state of the speaker. If this signal is corrupted by noise, this information may be lost or become difficult to hear.There are several speech enhancement methods such as spectral subtraction method, Wiener filter method and adaptive wiener filtering method. A proposed method of speech enhancement to reduce the degradation of speech signal is introduced in this paper depending on speech averaging, median filtering or minimum periodogram. This averaging method can be used as a preprocessing step in speaker identification. Simulation results show a good performance of the proposed speech enhancement method.

Keywords


Speech Recognition, Speech Enhancement, Speech Averaging, Spectral Subtraction,Wiener Filter, Adaptive Wiener Filter, Speech Quality Metrics.