This paper proposes a new audio post-production tool for speech dereverberation that utilizes our previously proposed method. In previous studies, we proposed a single-channel dereverberation method as preprocessing of automatic speech recognition and reported its good performance. This paper focuses more on the improvement of the audible quality of the dereverberated signals. To achieve good dereverberation with less audible artifacts, the previously proposed dereverberation method is combined with post-processing that implicitly considers the perceptual masking property. The system has three adjustable parameters for controlling audible quality. With an informal evaluation, we found that the proposed tool allows the professional audio engineers to dereverberate a set of reverberant recordings efficiently.

Authors: Kinoshita, Keisuke; Nakatani, Tomohiro; Miyoshi, Masato; Kubota, Toshiyuki
Affiliations: NTT Communication Science Laboratories; NTT Media Lab(See document for exact affiliation information.)
AES Convention: 125 (October 2008) Paper Number: 7615
Publication Date: October 1, 2008 Import into BibTeX
Subject: Spatial Audio Processing
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=14766

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 125Papers)   /125/7615.pdf

Start a discussion about this paper!