Effect of anti-aliasing filtering on the quality of speech from an HMM-based synthesizer

This paper investigates how the quality of speech produced through statistical parametric synthesis is affected by anti-aliasing filtering, i.e., low-pass filtering that is applied prior to (down-) sampling prerecorded speech at a desired rate. It has empirically been known that the frequency response of such anti-aliasing filters influences the quality of speech synthesized to a considerable degree. For the purpose of understanding such influence more clearly, in this paper we examine the spectral aspects of speech involved in the processes of HMM training and synthesis. We then propose a technique of feature extraction that can avoid producing the roll-off feature of the frequency response near the Nyquist frequency, which is found to be the major cause of speech quality degradation resulting from anti-aliasing filtering. In the technique, the spectrum is first computed from speech at a sampling rate higher than the desired rate, then it is truncated so that its frequency range above the target Nyquist frequency is discarded, and finally the truncated spectrum is converted directly into the cepstrum. Listening test results show that the proposed technique enables training HMMs efficiently with a limited number of model parameters and effectively with less artifacts in the speech synthesized at a desired sampling rate.