PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model

This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained prominence as non-autoregressive models that can generate high-quality waveforms....

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 12782 - 12786
Hlavní autori: Hono, Yukiya, Hashimoto, Kei, Nankaku, Yoshihiko, Tokuda, Keiichi
Médium: Konferenčný príspevok..
Jazyk:English
Japanese
Vydavateľské údaje: IEEE 14.04.2024
Predmet:
Controllability
diffusion probabilistic model
neural vocoder
pitch controllability
Probabilistic logic
Robustness
Signal processing
singing voice synthesis
Speech processing
Speech synthesis
Training
Vocoders
ISSN:2379-190X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained prominence as non-autoregressive models that can generate high-quality waveforms. The neural vocoders based on DDPM have the advantage of training with a simple time-domain loss. In practical applications, such as singing voice synthesis, there is a demand for neural vocoders to generate high-fidelity speech waveforms with flexible pitch control. However, conventional DDPM-based neural vocoders struggle to generate speech waveforms under such conditions. Our proposed model aims to accurately capture the periodic structure of speech waveforms by incorporating explicit periodic signals. Experimental results show that our model improves sound quality and provides better pitch control than conventional DDPM-based neural vocoders.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10448502