Publications-Detail

Real-Time Near-End Listening Enhancement for Mobile Phones

Authors:
Sauert, B.Heese, F.Vary, P.
Book Title:
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Organization:
IEEE
Date:
May. 2014
Note:

Show and Tell Demonstration

Language:
English

Abstract

Mobile telephony is often conducted in the presence of acoustical background noise such as traffic or babble noise. The near-end listener perceives a mixture of clean far-end (downlink) speech and background noise at the near-end side. Thus, the user experiences an increased listening effort and possibly a reduced speech intelligibility. This situation can be improved by adaptive signal processing of the far-end signal, which we call near-end listening enhancement (NELE). In our real-time demonstration the visitor will experience the strong improvement in the acoustic conference/exhibition environment. The adaptive algorithm optimizes the intelligibility of the far-end speech even in instationary background noise with respect to the objective criterion Speech Intelligibility Index (SII). In contrast to state-of-the-art techniques, the presented method considers the requirements and restrictions of realistic scenarios such as in mobile phones.

Download

BibTeX

Copyright © by IEEE
sauert14c.pdf
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.