Fine-grained Noise Control for Multispeaker Speech Synthesis

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 a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-10
Hauptverfasser: Nikitaras, Karolos, Vamvoukakis, Georgios, Ellinas, Nikolaos, Klapsas, Konstantinos, Markopoulos, Konstantinos, Raptis, Spyros, June Sig Sung, Jho, Gunu, Chalamandaris, Aimilios, Tsiakoulis, Pirros
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2204.05070