FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
Audio and Speech Processing
2021-06-30 v1 Machine Learning
Sound
Signal Processing
Abstract
Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large pitch-shift scale suffers from audio quality degradation, and speaker characteristics deformation. To address this problem, we propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. This model, called FastPitchFormant, has a unique structure that handles text and acoustic features in parallel. With modeling each feature separately, the tendency that the model learns the relationship between two features can be mitigated.
Cite
@article{arxiv.2106.15123,
title = {FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis},
author = {Taejun Bak and Jae-Sung Bae and Hanbin Bae and Young-Ik Kim and Hoon-Young Cho},
journal= {arXiv preprint arXiv:2106.15123},
year = {2021}
}
Comments
Accepted to INTERSPEECH 2021