Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features

no code implementations • 1 Nov 2022 • Alexandra Vioni, Georgia Maniati, Nikolaos Ellinas, June Sig Sung, Inchul Hwang, Aimilios Chalamandaris, Pirros Tsiakoulis

In modern high-quality neural TTS systems, prosodic appropriateness with regard to the spoken content is a decisive factor for speech naturalness.

POS Self-Supervised Learning

Generating Gender-Ambiguous Text-to-Speech Voices

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.

Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis

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.

Disentanglement Expressive Speech Synthesis

Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation

no code implementations • 31 Oct 2022 • Nikolaos Ellinas, Georgios Vamvoukakis, Konstantinos Markopoulos, Georgia Maniati, Panos Kakoulidis, June Sig Sung, Inchul Hwang, Spyros Raptis, Aimilios Chalamandaris, Pirros Tsiakoulis

When used in a cross-lingual setting, acoustic features are initially produced with a native speaker of the target language and then voice conversion is applied by the same model in order to convert these features to the target speaker's voice.

Disentanglement Voice Conversion

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

High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency

no code implementations • 17 Nov 2021 • Nikolaos Ellinas, Georgios Vamvoukakis, Konstantinos Markopoulos, Aimilios Chalamandaris, Georgia Maniati, Panos Kakoulidis, Spyros Raptis, June Sig Sung, Hyoungmin Park, Pirros Tsiakoulis

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications.

Speech Synthesis

Cross-lingual Low Resource Speaker Adaptation Using Phonological Features

no code implementations • 17 Nov 2021 • Georgia Maniati, Nikolaos Ellinas, Konstantinos Markopoulos, Georgios Vamvoukakis, June Sig Sung, Hyoungmin Park, Aimilios Chalamandaris, Pirros Tsiakoulis

Subsequently, we fine-tune the model with very limited data of a new speaker's voice in either a seen or an unseen language, and achieve synthetic speech of equal quality, while preserving the target speaker's identity.

Speech Synthesis

Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control

no code implementations • 17 Nov 2021 • Konstantinos Markopoulos, Nikolaos Ellinas, Alexandra Vioni, Myrsini Christidou, Panos Kakoulidis, Georgios Vamvoukakis, Georgia Maniati, June Sig Sung, Hyoungmin Park, Pirros Tsiakoulis, Aimilios Chalamandaris

In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice.

Singing Voice Synthesis