Alexander Sorin, Slava Shechtman, et al.
INTERSPEECH 2020
In statistical HMM-based text-to-speech systems (STTS), speech feature dynamics is modeled by first- and second-order feature frame differences, which, typically, do not satisfactorily represent frame to frame feature dynamics present in natural speech. The reduced dynamics results in over-smoothing of speech features, often sounding as muffled synthesized speech. In this correspondence, we propose a method to enhance a baseline STTS system by introducing a segment-wise model representation with a norm constraint. The segment-wise representation provides additional degrees of freedom in speech feature determination. We exploit these degrees of freedom for increasing the speech feature vector norm to match a norm constraint. As a result, statistically generated speech features are less over-smoothed, resulting in more natural sounding speech, as judged by listening tests. © 2006 IEEE.
Alexander Sorin, Slava Shechtman, et al.
INTERSPEECH 2020
Zvi Kons, Slava Shechtman, et al.
INTERSPEECH 2019
Alexander Sorin, Slava Shechtman, et al.
INTERSPEECH 2014
Noam Slonim, Yonatan Bilu, et al.
Nature