Fine-grained Noise Control for Multispeaker Speech Synthesis
Abstract
A text-to-speech (TTS) model typically factorizes speech attributes such as content, speaker and prosody into disentangled representations.Recent works aim to additionally model the acoustic conditions explicitly, in order to disentangle the primary speech factors, i.e. linguistic content, prosody and timbre from any residual factors, such as recording conditions and background noise.This paper proposes unsupervised, interpretable and fine-grained noise and prosody modeling. We incorporate adversarial training, representation bottleneck and utterance-to-frame modeling in order to learn frame-level noise representations. To the same end, we perform fine-grained prosody modeling via a Fully Hierarchical Variational AutoEncoder (FVAE) which additionally results in more expressive speech synthesis.
Cite
@article{arxiv.2204.05070,
title = {Fine-grained Noise Control for Multispeaker Speech Synthesis},
author = {Karolos Nikitaras and Georgios Vamvoukakis and Nikolaos Ellinas and Konstantinos Klapsas and Konstantinos Markopoulos and Spyros Raptis and June Sig Sung and Gunu Jho and Aimilios Chalamandaris and Pirros Tsiakoulis},
journal= {arXiv preprint arXiv:2204.05070},
year = {2022}
}
Comments
Accepted to INTERSPEECH 2022