Models that represent objective speech quality should include the influence of the cultural background of the listener as well as the particular language being spoken. Tests that evaluated American English and Igbo, an African tone language, revealed significant differences. Igbo listeners were more disturbed by additive noise and low listening levels. The low-level parts of the Igbo tone language appear to contain more critically important information than American English. Quality speech models must therefore be tuned to match the culture and language.

Authors: Ebem, Deborah U.; Beerends, John G.; Van Vugt, Jereon; Schmidmer, Christian; Kooij, Robert E.; Uguru, Joy O.
Affiliations: Department of Computer Science, University of Nigeria, Nsukka, Enugu-State, Nigeria; TNO, Delft, The Netherlands; OPTICOM GmbH, Erlangen, Germany; Delft University of Technology, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft, The Netherlands; Department of Linguistics, Igbo and other Nigerian Languages, University of Nigeria, Nsukka, Nigeria (See document for exact affiliation information.)
JAES Volume 59 Issue 9 pp. 647-655; September 2011
Publication Date: October 10, 2011

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.