Picture for Georgia Maniati

Georgia Maniati

Improved Text Emotion Prediction Using Combined Valence and Arousal Ordinal Classification

Add code
Apr 02, 2024
Viaarxiv icon

Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations

Add code
Feb 02, 2024
Viaarxiv icon

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

Add code
Nov 01, 2022
Figure 1 for Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
Figure 2 for Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
Figure 3 for Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
Figure 4 for Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
Viaarxiv icon

Generating Gender-Ambiguous Text-to-Speech Voices

Add code
Nov 01, 2022
Figure 1 for Generating Gender-Ambiguous Text-to-Speech Voices
Figure 2 for Generating Gender-Ambiguous Text-to-Speech Voices
Figure 3 for Generating Gender-Ambiguous Text-to-Speech Voices
Figure 4 for Generating Gender-Ambiguous Text-to-Speech Voices
Viaarxiv icon

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

Add code
Nov 01, 2022
Figure 1 for Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis
Figure 2 for Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis
Figure 3 for Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis
Figure 4 for Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis
Viaarxiv icon

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

Add code
Oct 31, 2022
Figure 1 for Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
Figure 2 for Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
Figure 3 for Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
Figure 4 for Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
Viaarxiv icon

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

Add code
Apr 06, 2022
Figure 1 for SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
Figure 2 for SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
Figure 3 for SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
Figure 4 for SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
Viaarxiv icon

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

Add code
Nov 17, 2021
Figure 1 for Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control
Figure 2 for Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control
Figure 3 for Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control
Figure 4 for Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control
Viaarxiv icon

Cross-lingual Low Resource Speaker Adaptation Using Phonological Features

Add code
Nov 17, 2021
Figure 1 for Cross-lingual Low Resource Speaker Adaptation Using Phonological Features
Figure 2 for Cross-lingual Low Resource Speaker Adaptation Using Phonological Features
Figure 3 for Cross-lingual Low Resource Speaker Adaptation Using Phonological Features
Viaarxiv icon

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

Add code
Nov 17, 2021
Figure 1 for High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
Figure 2 for High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
Figure 3 for High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
Viaarxiv icon