Word-wise intonation model for cross-language TTS systems
This work addresses intonation modeling for text-to-speech systems, particularly for Russian and potentially other languages, but appears incremental as it builds on existing intonation systems and methods.
The authors tackled the problem of intonation variability in cross-language text-to-speech systems by proposing a word-wise intonation model for Russian, which reduces variability related to stressed syllable placement using pitch simplification and dynamic time warping clustering, and demonstrated its robustness to parameter variations.
In this paper we propose a word-wise intonation model for Russian language and show how it can be generalized for other languages. The proposed model is suitable for automatic data markup and its extended application to text-to-speech systems. It can also be implemented for an intonation contour modeling by using rule-based algorithms or by predicting contours with language models. The key idea is a partial elimination of the variability connected with different placements of a stressed syllable in a word. It is achieved with simultaneous applying of pitch simplification with a dynamic time warping clustering. The proposed model could be used as a tool for intonation research or as a backbone for prosody description in text-to-speech systems. As the advantage of the model, we show its relations with the existing intonation systems as well as the possibility of using language models for prosody prediction. Finally, we demonstrate some practical evidence of the system robustness to parameter variations.