Project Overview
A curated overview of independently identifiable research and resources for generating Kurdish speech from text. It covers Sorani and Kurmanji studies, TTS-oriented speech corpora, and released synthesis resources. Each record credits its original creators and distinguishes published research, corpora, and externally released tools from KaiLab-owned work.
Technologies & Methods
Applications
- Speech Synthesis
- Accessibility
- Audiobooks
- Educational Tools
Related Publications
A comparison between allophone, syllable, and diphone based TTS systems for Kurdish language
Wafa Barkhoda , Bahram ZahirAzami , Anvar Bahrampour , Om-Kolsoom Shahryari (2009)
A historical Kurdish text-to-speech study comparing concatenative synthesis systems based on allophone, syllable, and diphone units. The retrieved primary bibliographic metadata verifies the …
Central Kurdish Text-to-Speech and Its Application in Speech-to-Text Translation
Mohammad Mohammadamini , Meysam Shamsi , Marie Tahon (2026)
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 …
Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training
Hawraz A. Ahmad , Tarik A. Rashid (2024)
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 …
Kurdish end-to-end speech synthesis using deep neural networks
Sabat Salih Muhamad , Hadi Veisi , Aso Mahmudi , Abdulhady Abas Abdullah , Farhad Rahimi (2024)
A Central Kurdish end-to-end speech synthesis study comparing Tacotron 2 and WaveGlow configurations, including transfer learning from English and training from scratch. The work uses a single-speaker …
End-to-End Kurdish Speech Synthesis Based on Transfer Learning
Sabat Muhamad , Hadi Veisi (2022)
A Sorani Kurdish speech synthesis study using transfer learning from an English Tacotron 2 model with a pretrained HiFi-GAN vocoder. The experiment uses a single female speaker corpus of approximately …
Gigant-KTTS dataset: Towards building an extensive gigant dataset for Kurdish text-to-speech systems
Hawraz A. Ahmad , Tarik A. Rashid (2024)
A dataset paper describing Gigant-KTTS, a Central Kurdish speech corpus constructed specifically for text-to-speech research. The corpus contains 6,078 recorded sentences across twelve subject …
Adapting F5-TTS Model to Kurdish Sorani: Diffusion-based Speech Synthesis with a Specialized Dataset
Hamreen Ahmad , Aree Mohammed (2025)
A Sorani Kurdish speech synthesis study adapting F5-TTS with a specialized single-speaker collection derived from broadcast material. The paper reports subjective and recognition-based evaluation; the …
Deep Learning-Based Text-to-Speech Synthesis for Central Kurdish: A Transformer-Enhanced Approach
Salman Burhan Ahmed , Sozan Abdullah Mahmood (2026)
A Central Kurdish speech synthesis study combining a CNN-Transformer encoder, Tacotron 2 autoregressive decoding, and WaveGlow. The experiment reuses Gigant-KTTS recordings and evaluates synthesized …
Scaling Speech Technology to 1,000+ Languages
Vineel Pratap , Andros Tjandra , Bowen Shi , Paden Tomasello , Arun Babu , Sayani Kundu , Ali Elkahky , Zhaoheng Ni , Apoorv Vyas , Maryam Fazel-Zarandi , Alexei Baevski , Yossi Adi , Xiaohui Zhang , Wei-Ning Hsu , Alexis Conneau , Michael Auli (2024)
A multilingual speech technology study associated with Meta's Massively Multilingual Speech project. Its Kurdish relevance includes released Northern Kurdish/Kurmanji VITS synthesis checkpoints with …
Related Datasets
Gigant-KTTS / Gigant Dataset
Published: April 2, 2024 | Size: 6,078 utterances; 13.63 hours reported
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, …
TTS4All Central Kurdish Speech Dataset
Published: January 1, 2026 | Size: 17,671 utterances / 35h20m reported; inspected release contained 17,738 metadata rows
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 …
AsoSoft Speech Corpus for Central-Kurdish Text-To-Speech
Published: June 17, 2022 | Size: Public subset: approximately 1h02m and 522 text/audio pairs
A Central Kurdish single-speaker female speech corpus associated with AsoSoft. The full corpus is described as 21 hours and 10,979 sentences, but the public repository offers only an approximately …
KurFemTTS: A Large-Scale Kurdish Female Speech Corpus for Text-to-Speech
Published: July 8, 2026 | Size: 4,599 WAV files inspected; 2,993 metadata rows; approximately 10 hours reported
A Sorani/Central Kurdish female speech corpus released by Abdulhady A. Abdullah, Tarik A. Rashid, Tanya Syamand, Polla A. Fattah, Qais kakl, and Pakhshan fahmi. The creator reports approximately ten …
SoraniTTS dataset: Central Kurdish (CK) Speech Corpus for Text-to-Speech
Published: September 16, 2025 | Size: 6,565 sentence/audio pairs; approximately 19 hours reported
A Central Kurdish/Sorani speech corpus by Farhad Rahimi, Nafiseh Osati Eraghi, and Hadi Veisi. The v5 resource reports 6,565 sentence/audio pairs and approximately 19 hours from one male studio …