A Novel End-to-End Turkish Text-to-Speech (TTS) System via Deep Learning
Electronics · 18.04.2023 · 12 (8) · 1900
DOI: 10.3390/electronics12081900 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 18.04.2023. Verfasst von Saadin Oyucu. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific and Technological Research Council of Turkey.
Abstract (Originalsprache)
Text-to-Speech (TTS) systems have made strides but creating natural-sounding human voices remains challenging. Existing methods rely on noncomprehensive models with only one-layer nonlinear transformations, which are less effective for processing complex data such as speech, images, and video. To overcome this, deep learning (DL)-based solutions have been proposed for TTS but require a large amount of training data. Unfortunately, there is no available corpus for Turkish TTS, unlike English, which has ample resources. To address this, our study focused on developing a Turkish speech synthesis system using a DL approach. We obtained a large corpus from a male speaker and proposed a Tacotron 2 + HiFi-GAN structure for the TTS system. Real users rated the quality of synthesized speech as 4.49 using Mean Opinion Score (MOS). Additionally, MOS-Listening Quality Objective evaluated the speech quality objectively, obtaining a score of 4.32. The speech waveform inference time was determined by a real-time factor, with 1 s of speech data synthesized in 0.92 s. To the best of our knowledge, these findings represent the first documented deep learning and HiFi-GAN-based TTS system for Turkish TTS.
Förderung
- Scientific and Technological Research Council of Turkey
Zitieren
APA
Oyucu, S. (2023). A Novel End-to-End Turkish Text-to-Speech (TTS) System via Deep Learning. Electronics, 12(8), 1900. https://doi.org/10.3390/electronics12081900
Vancouver
Oyucu S. A Novel End-to-End Turkish Text-to-Speech (TTS) System via Deep Learning. Electronics. 2023;12(8):1900. doi:10.3390/electronics12081900
BibTeX
@article{Oyucu2023,
author = {Oyucu, Saadin},
title = {A Novel End-to-End Turkish Text-to-Speech (TTS) System via Deep Learning},
journal = {Electronics},
year = {2023},
volume = {12},
number = {8},
pages = {1900},
doi = {10.3390/electronics12081900}
}
EUVIMED