Dual-Channel Speech Enhancement Using a Perceptual Filterbank for Hands-Free Communication - Digital Signal Processing for In-Vehicle Systems and Safety - page 176

Chapter 12
Dual-Channel Speech Enhancement Using
a Perceptual Filterbank for Hands-Free
Communication

Jongsung Yoon, Kihyeon Kim, Jounghoon Beh, Robert H. Baran,
and Hanseok Ko

Abstract We investigate a dual-channel speech enhancement method using
perceptual adaptive noise suppressor, which improves perceptual quality of speech
in automobile environment for hands-free communication. In particular, the per-
ceptual adaptive noise suppressor, which is composed of a Mel-based perceptual
filterbank, an adaptive filter, and a speech modification block, estimates the enve-
lope of the desired speech by suppressing the nonspeech components. Experiments
indicate that the proposed scheme shows 8.06 dB of NR improvement and 0.70 of
PESQ score improvement compared to the Transfer Function Generalized Sidelobe
Canceller structure alone.

Keywords Driver assistance • Dual-channel speech enhancement • Hands-free
communication • In-vehicle speech technology

12.1 Introduction

Recently, the significance of multi-microphone-based speech enhancement has
increased as the needs of hands-free communication systems grow, especially in
in-vehicle situations. In this chapter, an efficient multichannel speech enhancement
algorithm is presented, which improves the speech quality while minimizing the
directional interference and ambient noise.

J. Yoon • K. Kim • R.H. Baran • H. Ko ( * )
Department of Electronics and Computer Engineering, Korea University, 5Ka-1 Anam-dong,
Seongbuk-Gu, Seoul 136713, South Korea
e-mail: [e-mail]
J. Beh
Institute for Advanced Computer Studies, University of Maryland, College Park, MD, USA