A large part of the expressive speech synthesis literature focuses on learning prosodic representations of the speech signal which are then modeled by a prior distribution during inference.
no code implementations • 1 Nov 2022 • Konstantinos Markopoulos, Georgia Maniati, Georgios Vamvoukakis, Nikolaos Ellinas, Karolos Nikitaras, Konstantinos Klapsas, Georgios Vardaxoglou, Panos Kakoulidis, June Sig Sung, Inchul Hwang, Aimilios Chalamandaris, Pirros Tsiakoulis, Spyros Raptis
While a female voice is a common choice, there is an increasing interest in alternative approaches where the gender is ambiguous rather than clearly identifying as female or male.
no code implementations • 1 Nov 2022 • Karolos Nikitaras, Konstantinos Klapsas, Nikolaos Ellinas, Georgia Maniati, June Sig Sung, Inchul Hwang, Spyros Raptis, Aimilios Chalamandaris, Pirros Tsiakoulis
We show that the fine-grained latent space also captures coarse-grained information, which is more evident as the dimension of latent space increases in order to capture diverse prosodic representations.
no code implementations • 11 Apr 2022 • Karolos Nikitaras, Georgios Vamvoukakis, Nikolaos Ellinas, Konstantinos Klapsas, Konstantinos Markopoulos, Spyros Raptis, June Sig Sung, Gunu Jho, Aimilios Chalamandaris, Pirros Tsiakoulis
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.
no code implementations • 7 Apr 2022 • Konstantinos Klapsas, Nikolaos Ellinas, Karolos Nikitaras, Georgios Vamvoukakis, Panos Kakoulidis, Konstantinos Markopoulos, Spyros Raptis, June Sig Sung, Gunu Jho, Aimilios Chalamandaris, Pirros Tsiakoulis
This method enables us to train our model in an unlabeled multispeaker dataset as well as use unseen speaker embeddings to copy a speaker's voice.
In this work, we present the SOMOS dataset, the first large-scale mean opinion scores (MOS) dataset consisting of solely neural text-to-speech (TTS) samples.