Central Kurdish Text-to-Speech and Its Application in Speech-to-Text Translation
Authors
Proceedings of the Fifteenth Language Resources and Evaluation Conference
pp. 664-673
May 1, 2026
Abstract
A Central Kurdish text-to-speech study presenting three separately fine-tuned single-speaker F5-TTS models trained on two audiobook-derived resources and reused Gigant recordings. The study evaluates synthesized speech with human listeners and applies synthetic speech to downstream speech translation.
Keywords
Central Kurdish
Sorani
F5-TTS
Speech Synthesis
Speech Translation
Related Datasets
TTS4All Central Kurdish Speech Dataset
2026
17,671 utterances / 35h20m reported; inspected release contained 17,738 metadata rows
WAV, CSV
A Central Kurdish TTS corpus released by Mohammad Mohammadamini, Meysam Shamsi, Marie Tahon, TTS4All/JSALT 2025, and LIUM. Published statistics report 17,671 utterances and 35h20m, while the inspected …
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
Mohammadamini, M., Shamsi, M., & Tahon, M. (2026). Central Kurdish Text-to-Speech and Its Application in Speech-to-Text Translation. Proceedings of the Fifteenth Language Resources and Evaluation Conference, 664–673. https://doi.org/10.63317/4hfwowidu34u