Syllabic Pitch Tuning for Neutral-to-emotional Voice Conversion

Prosody plays an important role in neutral-to-emotional voice conversion. Prosodic features like pitch are usually estimated and altered at a segmental level based on short windowing of speech signal (where the signal is expected to be quasi-stationary). This results in a frame-wise change of acoustical parameters for synthesizing emotionalized speech. In order to convert a neutral speech to an emotional speech from the same user, it might be better to tune the pitch trajectory at the supra-segmental level like at the syllable-level since the changes in the signal are more subtle and smooth. In this paper we aim to show that the pitch tuning in a neutral-to-emotional voice conversion system may result in a better speech quality output if the tuning is performed at the supra-segmental (syllable) level rather than at frame-level. Subjective evaluation results are shown to demonstrate the improvements in terms of naturalness and speaker similarity.