Results on Automated Tuning of a Voice Quality Enhancement System Using Objective Quality Measures
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.
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.
The Engineering Briefs at this Convention were selected on the basis of a submitted synopsis, ensuring that they are of interest to AES members, and are not overly commercial. These briefs have been reproduced from the authors' advance manuscripts, without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for their contents. Paper copies are not available, but any member can freely access these briefs. Members are encouraged to provide comments that enhance their usefulness.