Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training
Authors
Algorithms
Vol. 17
July 3, 2024
Abstract
An end-to-end Central Kurdish text-to-speech study using latent speech representations, text-audio alignment, adversarial waveform training, and duration prediction. The system is evaluated on the Gigant-KTTS corpus. Reported quality and speed measurements belong to the cited experiment and are not independently reproduced here.
Keywords
Central Kurdish
Sorani
Text-to-Speech
Transformer
Speech Synthesis
Related Datasets
Gigant-KTTS / Gigant Dataset
2024
6,078 utterances; 13.63 hours reported
WAV, XLSX
A Central Kurdish speech corpus created for text-to-speech research by Hawraz A. Ahmad and Tarik A. Rashid. The release reports 6,078 utterances from one male speaker across twelve subject categories, …
Citation
Ahmad, H. A., & Rashid, T. A. (2024). Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training. Algorithms, 17(7), 292. https://doi.org/10.3390/a17070292