Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch

TL;DR

This paper introduces two algorithms to enhance pitch controllability in FastPitch TTS by using timbre-preserving pitch augmentation and diverse pitch-range training, resulting in more natural and robust speech synthesis.

Contribution

The paper presents a novel timbre-preserving pitch-shifting algorithm and a training method with augmented pitch datasets to improve FastPitch's pitch control robustness.

Findings

Improved pitch controllability in FastPitch.

Enhanced naturalness of pitch-shifted speech.

Robustness across diverse pitch ranges.

Abstract

The recently developed pitch-controllable text-to-speech (TTS) model, i.e. FastPitch, was conditioned for the pitch contours. However, the quality of the synthesized speech degraded considerably for pitch values that deviated significantly from the average pitch; i.e. the ability to control pitch was limited. To address this issue, we propose two algorithms to improve the robustness of FastPitch. First, we propose a novel timbre-preserving pitch-shifting algorithm for natural pitch augmentation. Pitch-shifted speech samples sound more natural when using the proposed algorithm because the speaker's vocal timbre is maintained. Moreover, we propose a training algorithm that defines FastPitch using pitch-augmented speech datasets with different pitch ranges for the same sentence. The experimental results demonstrate that the proposed algorithms improve the pitch controllability of FastPitch.