"In this paper we use a time-frequency based measure, the stationarity index, to characterize the non stationary behavior of languages. We show that different languages have different non stationary behavior. This is done in order to explain why speech processing systems relying on frame by frame analysis in the frequency domain, have a language dependent behavior. This dependency is demonstrated using the case of PESQ, the Perceptual Evaluation of Speech Quality model, which enables objective assessment of speech quality."
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.