Generating Multilingual Gender-Ambiguous Text-to-Speech Voices

no code implementations • 1 Nov 2022 • Konstantinos Markopoulos, Georgia Maniati, Georgios Vamvoukakis, Nikolaos Ellinas, Georgios Vardaxoglou, Panos Kakoulidis, Junkwang Oh, Gunu Jho, Inchul Hwang, Aimilios Chalamandaris, Pirros Tsiakoulis, Spyros Raptis

The gender of any voice user interface is a key element of its perceived identity.

Fine-grained Noise Control for Multispeaker Speech Synthesis

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.

Expressive Speech Synthesis

Karaoker: Alignment-free singing voice synthesis with speech training data

no code implementations • 8 Apr 2022 • Panos Kakoulidis, Nikolaos Ellinas, Georgios Vamvoukakis, Konstantinos Markopoulos, June Sig Sung, Gunu Jho, Pirros Tsiakoulis, Aimilios Chalamandaris

Existing singing voice synthesis models (SVS) are usually trained on singing data and depend on either error-prone time-alignment and duration features or explicit music score information.

Singing Voice Synthesis Speaker Identification

Self-supervised learning for robust voice cloning

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.

Self-Supervised Learning Speech Synthesis +1

SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis

no code implementations • 6 Apr 2022 • Georgia Maniati, Alexandra Vioni, Nikolaos Ellinas, Karolos Nikitaras, Konstantinos Klapsas, June Sig Sung, Gunu Jho, Aimilios Chalamandaris, Pirros Tsiakoulis

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.

Speech Synthesis Text-To-Speech Synthesis