Abstract

This paper deals with speech enhancement in hands-free telecommunication systems. The two major problems encountered in such contexts - noise reduction and acoustic echo cancellation - are addressed. After the presentation of the two basic cascaded structures found in the literature, we propose a new promising technique which takes advantage of the previous ones. The main objective is to get a near-end speech signal with low levels of distortion, echo and noise. The structure is tested in a real mobile environment and compared with the two others. An objective evaluation shows the improvement provided by this structure.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call