In this work we present a formal procedure for automating the tuning of the various parameters comprising a voice quality enhancer. First, we formalize the problem of tuning as a large-scale nonlinear programming problem. Second, we evaluate the performance of perceptual objective quality measures as optimization criteria for our tuning problem. We then perform a subjective quality assessment to compare the output of a voice enhancer obtained with parameters calculated with these different criteria and also with those obtained through a conventional approach of tuning by expert listening. The results show that using this automated methodology performs well in finding reasonable solutions for the tuning problem, potentially saving time and resources over manual evaluation and tuning.
(See document for exact affiliation information.)
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 Join the AES. If you need to check your member status, login to the Member Portal.
