Improving speech synthesis quality by reducing pitch peaks in the source recordings

Luisina Violante, Pablo Rodriguez Zivic and Agustin Gravano

We present a method for improving the perceived naturalness of corpus-based speech synthesizers. It consists in removing pronounced pitch peaks in the original recordings, which typically lead to noticeable discontinuities in the synthesized speech. We perceptually evaluated this method using two concatenative and two HMM-based synthesis systems, and found that using it on the source recordings managed to improve the naturalness of the synthesizers and had no effect on their intelligibility.