Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch
This work addresses a specific limitation in pitch-controllable text-to-speech models for speech synthesis applications, representing an incremental improvement.
The paper tackled the problem of degraded speech quality in FastPitch when controlling pitch values far from the average, by proposing a timbre-preserving pitch-shifting algorithm and a training method using pitch-augmented datasets, resulting in improved pitch controllability.
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.