Improving Naturalness of Neural-based TTS System Trained with Arabic Limited Data

View/ Open
Metadata
Show full item record
Link to refer to this document:
Abstract
In this paper, we investigated different approaches, a neural network speech synthesis system and a non-autoregressive text-to-speech (TTS) model. In the neural network speech synthesis, we showed how a baseline system based on Merlin is used for TTS synthesis to produce the most human-like voice; typically, it is only implemented with a front-end text processor and a WORLD vocoder. Here, we first adapted Continuous and Ahocoder vocoders; and then we investigated the effectiveness of each vocoder’s techniques to produce the highest quality speech. In the non-autoregressive TTS model, we implemented the state-of-the-results Fastspeech2 system, which provided high-quality speech synthesis in a timely manner without controllability and robustness problems. Here, we focused on integrating a different language but with limited data while maintaining its high-quality produced sounds. Through objective and subjective evaluations, we verify that our method can outperform the baseline system with full data.- Title
- Improving Naturalness of Neural-based TTS System Trained with Arabic Limited Data
- Author
- Sawalha, Layan
- Alradhi, Mohammad
- Date of issue
- 2023
- Access level
- Open access
- Copyright owner
- Szerző
- Conference title
- 1st Workshop on Intelligent Infocommunication Networks, Systems and Services (WI2NS2)
- Conference place
- Budapest
- Conference date
- 2023.02.07
- Language
- en
- Page
- 71 - 75
- Subject
- Text-to-speech, TTS, Machine Learning, Deep Learning, Deep Neural Networks, Speech Synthesis
- Version
- Post print
- Identifiers
- DOI: 10.3311/WINS2023-013
- Title of the container document
- 1st Workshop on Intelligent Infocommunication Networks, Systems and Services
- ISBN, e-ISBN
- 978-963-421-902-6
- Document type
- Konferenciaközlemény
- Document genre
- Konferenciacikk
- University
- Budapest University of Technology and Economics
- Faculty
- Faculty of Electrical Engineering and Informatics