High-Quality Analysis/Synthesis Method Based on Temporal Decomposition for Speech Modification

The challenge of speech modification is to flexibly modify the speech without degrading speech quality. The conventional methods are limited by their inability to flexibly control speech signals in time and frequency domains. This causes degradation of the quality of modified speech. This paper proposes a high-quality analysis/synthesis method for speech modification. To control the temporal evolution, we use a speech analysis technique called temporal decomposition (TD), which decomposes a speech signal into event targets and event functions. The same event functions evaluated for the spectral parameters are also used to model the temporal evolution of the excitation parameters. The event functions describe the temporal evolution of the spectral and excitation parameters, and the event targets represent the "ideal" spectral parameters. To flexibly control speech signals in both time and frequency domains, we propose new methods to model the event functions and the event targets. The experimental results show that our proposed analysis/synthesis method produces high-quality synthesized speech, and allows the flexibility to modify speech signals.