27 citations · 99 across the 19 of their papers we have counts for
19 papers
Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders
Nikolaos Ellinas, Alexandra Vioni, Panos Kakoulidis +8
This paper introduces a cepstrum-based pitch modification method that can be applied to any mel-spectrogram representation. As a result, this method is compatible with any mel-base…
MambaRate: Speech Quality Assessment Across Different Sampling Rates
Panos Kakoulidis, Iakovi Alexiou, Junkwang Oh +4
We propose MambaRate, which predicts Mean Opinion Scores (MOS) with limited bias regarding the sampling rate of the waveform under evaluation. It is designed for Track 3 of the Aud…
Improved Text Emotion Prediction Using Combined Valence and Arousal Ordinal Classification
Michael Mitsios, Georgios Vamvoukakis, Georgia Maniati +13
Emotion detection in textual data has received growing interest in recent years, as it is pivotal for developing empathetic human-computer interaction systems. This paper introduce…
Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations
Panos Kakoulidis, Nikolaos Ellinas, Georgios Vamvoukakis +8
In this paper, we propose a singing voice synthesis model, Karaoker-SSL, that is trained only on text and speech data as a typical multi-speaker acoustic model. It is a low-resourc…
Controllable speech synthesis by learning discrete phoneme-level prosodic representations
Nikolaos Ellinas, Myrsini Christidou, Alexandra Vioni +4
In this paper, we present a novel method for phoneme-level prosody control of F0 and duration using intuitive discrete labels. We propose an unsupervised prosodic clustering proces…
Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis
Konstantinos Klapsas, Karolos Nikitaras, Nikolaos Ellinas +5
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 i…
Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis
Karolos Nikitaras, Konstantinos Klapsas, Nikolaos Ellinas +6
This paper proposes an Expressive Speech Synthesis model that utilizes token-level latent prosodic variables in order to capture and control utterance-level attributes, such as cha…
Generating Multilingual Gender-Ambiguous Text-to-Speech Voices
Konstantinos Markopoulos, Georgia Maniati, Georgios Vamvoukakis +9
The gender of any voice user interface is a key element of its perceived identity. Recently, there has been increasing interest in interfaces where the gender is ambiguous rather t…
Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
Alexandra Vioni, Georgia Maniati, Nikolaos Ellinas +4
Current state-of-the-art methods for automatic synthetic speech evaluation are based on MOS prediction neural models. Such MOS prediction models include MOSNet and LDNet that use s…
Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
Nikolaos Ellinas, Georgios Vamvoukakis, Konstantinos Markopoulos +7
This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's langu…
Fine-grained Noise Control for Multispeaker Speech Synthesis
Karolos Nikitaras, Georgios Vamvoukakis, Nikolaos Ellinas +7
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 th…
Karaoker: Alignment-free singing voice synthesis with speech training data
Panos Kakoulidis, Nikolaos Ellinas, Georgios Vamvoukakis +5
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 info…
Self-supervised learning for robust voice cloning
Konstantinos Klapsas, Nikolaos Ellinas, Karolos Nikitaras +8
Voice cloning is a difficult task which requires robust and informative features incorporated in a high quality TTS system in order to effectively copy an unseen speaker's voice. I…
SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
Georgia Maniati, Alexandra Vioni, Nikolaos Ellinas +6
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. It can be employed to…
Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis
Alexandra Vioni, Myrsini Christidou, Nikolaos Ellinas +7
This paper presents a method for controlling the prosody at the phoneme level in an autoregressive attention-based text-to-speech system. Instead of learning latent prosodic featur…
Improved Prosodic Clustering for Multispeaker and Speaker-independent Phoneme-level Prosody Control
Myrsini Christidou, Alexandra Vioni, Nikolaos Ellinas +7
This paper presents a method for phoneme-level prosody control of F0 and duration on a multispeaker text-to-speech setup, which is based on prosodic clustering. An autoregressive a…
Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control
Konstantinos Markopoulos, Nikolaos Ellinas, Alexandra Vioni +8
In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice. It utilizes a Tacotron-based multispeaker acoustic model trained on read…
Cross-lingual Low Resource Speaker Adaptation Using Phonological Features
Georgia Maniati, Nikolaos Ellinas, Konstantinos Markopoulos +5
The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approa…
High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
Nikolaos Ellinas, Georgios Vamvoukakis, Konstantinos Markopoulos +7
This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based…