The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 31-515
Full Name: Elahe Kani
Position: Researcher
Age: ON
Sex: Female
Address: Department of Information Systems and Computing, Brunel University, Uxbridge, Middlesex UB8 3PH
Country: UNITED KINGDOM
Tel:
Tel prefix:
Fax:
E-mail address: elahe.kani@brunel.ac.uk
Other E-mails:
Title of the Paper: A new method for Speech Signals Enhancement Using LPC Analysis in base Spectral Subtraction, Multi-Band and Inverse Fourier Methods
Authors as they appear in the Paper: Mostafa Heydari; Aryan Salmanpour; Elahe Kani-Zabihi
Email addresses of all the authors: m.heydari@shomal.ac.ir , aryan_salmanpour@ee.iust.ac.ir, elahe.kani@brunel.ac.uk
Number of paper pages: 10
Abstract: In this paper we have supposed three methods for speech signal enhancement, which are based on Power Spectral Subtraction (PSS), Inverse Fourier Spectral Subtraction (IFSS) and Multi-Band Spectral Subtraction (MBSS) methods respectively. We have used Linear Predictive Coding (LPC), VAD analysis, and Voice/Unvoice (V/UV) detector for noise estimation and extraction, then we have compared the proposed methods with previously suggested ones. There is a noticeable improvement obtained in speech signal quality compared to previous methods. Also good results have been achieved in the auditory tests.
Keywords: Speech Enhancement, Noise, Spectral Subtraction, LPC analysis, VAD, V/UV detector
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Library, Bannerman Centre, Brunel University, Uxbridge, Middlesex, UB8 3PH
IP ADDRESS: 134.83.1.233
