Mobile phones include noise suppression to facilitate use in noisy environments; therefore listening tests in accordance with ITU-T P.835 are appropriate for comparing handset performance. Objective speech quality measures are an often used cheaper alternative; however the results can be misleading, as rank order compared to listening tests is not always preserved. We compare the outputs of PESQ, POLQA, and 3Quest with the results of P.835 listening tests. As expected, measures intended for use with noise suppression perform that task better than tools that were not initially designed to do so. However, improved measures, that aim to preserve rank order while minimizing both maximum error and RMSE, would improve the reliability of comparative evaluations in background noise.
Authors:
Francois, Holly; Isabelle, Scott; Oh, Eunmi
Affiliations:
Samsung Electronics R&D Institute UK, Staines-Upon Thames, Surrey, UK; Knowles Inc., Mountain View, CA, USA; Samsung Electronics Co., Ltd., Seoul, Korea(See document for exact affiliation information.)
AES Convention:
140 (May 2016)
Paper Number:
9532
Publication Date:
May 26, 2016
Subject:
Audio Quality
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.
To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.
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.