Recovery of broadband speech from narrowband speech by radial basis function neural networks

Author

Watanabe, Tonioini ; Murakami, Takahiro ; Namba, Masanori ; Hoya, Tetsuya ; Ishida, Yoshihisa

Author_Institution

Sch. of Sci. & Technol., Meiji Univ., Kawasaki, Japan

Volume

1

fYear

2002

fDate

28-31 Oct. 2002

Firstpage

469

Abstract

This paper presents a novel method to recovery of broadband speech from narrowband speech. The approach is based on estimating independently the spectral envelope using a radial basis function (RBF) neural network, a well-known model of artificial neural networks and the excitation function. The simulation results show that the proposed method is effective in the estimation of missing frequency components. Moreover, in listening tests, around 84% of the mean opinion score (MOS) was obtained by implementing the proposed recovery scheme.

Keywords

broadband networks; radial basis function networks; speech processing; telecommunication computing; telephony; artificial neural networks; broadband speech recovery; excitation function; mean opinion score; missing frequency component estimation; narrowband speech; radial basis function neural networks; simulation; spectral envelope; Artificial neural networks; Biological neural networks; Educational technology; Frequency estimation; Narrowband; Radial basis function networks; Signal processing; Speech processing; Telephony; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering

Print_ISBN

0-7803-7490-8

Type

conf

DOI

10.1109/TENCON.2002.1181315

Filename

1181315