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
Subject: Spatial Audio Processing

Click to purchase paper as a non-member or you can login as an AES member to see more options.

No AES members have commented on this paper yet.

Subscribe to this discussion

To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.

Start a discussion!

If you would like to start a discussion about this paper and are an AES member then you can login here:
Username:
Password:

If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.