Experiments with One-Class Classifier as a Predictor of Spectral Discontinuities in Unit Concatenation

摘要

We present a sequence of experiments with one-class classification, aimed at examining the ability of such a classifier to detect spectral smoothness of units, as an alternative to heuristics-based measures used within unit selection speech synthesizers. A set of spectral feature distances was computed between neighbouring frames in natural speech recordings, i.e. those representing natural joins, from which the per-vowel classifier was trained. In total, three types of classifiers were examined for distances computed from several different signal parame-trizations. For the evaluation, the trained classifiers were tested against smooth or discontinuous joins as they were perceived by human listeners in the ad-hoc listening test designed for this purpose.