Word-wise intonation model for cross-language TTS systems

TL;DR

This paper introduces a word-wise intonation model for Russian that can be adapted for other languages, simplifying prosody modeling in TTS systems through pitch normalization and clustering techniques.

Contribution

The paper presents a novel intonation model that reduces variability in stressed syllable placement and integrates with language models for improved prosody prediction.

Findings

Model effectively normalizes pitch variability across words.

Applicable to multiple languages with potential for TTS integration.

Demonstrates robustness to parameter variations.

Abstract

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.