Our Team

Author of verified Kurdish lexical-resource research included in this project.

Author of verified Kurdish lexical-resource research included in this project.

Coauthor of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Coauthor of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Researcher and coauthor of work on handwritten Sorani Kurdish text recognition and the DASNUS dataset.

Researcher associated with the University of Kurdistan Hewlêr and its Artificial Intelligence and Innovation Centre, with work on Central and Northern Kurdish automatic speech recognition and related speech technologies.

Coauthor of published research on handwritten Central Kurdish character data.

Author of verified Kurdish spelling-correction research included in this project.

Researcher in terminology-dictionary construction and concept-based terminology analysis.

Researcher and co-author of the 2019 experimental Sorani Kurdish speech-to-text study and the BD-4SK-ASR resource.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Coauthor of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher contributing to verified Kurdish language-resource research.

Co-author of verified research comparing allophone-, syllable-, and diphone-based text-to-speech systems for Kurdish.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Co-author of research adapting F5-TTS for Sorani Kurdish speech synthesis.

Coauthor of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher in Kurdish speech technology. Co-author of Jira and later Northern Kurdish Transformer-based automatic speech recognition research.

Co-author of verified research comparing allophone-, syllable-, and diphone-based text-to-speech systems for Kurdish.

Researcher and coauthor of work on terminology and the Kurdish lexicon.

Coauthor of the Kurdish Standard EMNIST-like character dataset publication.

Researcher and coauthor of verified work on OCR for historical printed Sorani Kurdish publications.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher in multilingual and less-resourced language NLP and co-creator of LR-Sum.

Researcher in multilingual and less-resourced natural language processing and co-creator of LR-Sum.

Researcher in Kurdish scientific translation and language conventions.

Researcher in Kurdish language and speech resources associated with Koya University and international research collaborations. Co-author of FLEURS-Kobani and CORDI-related work.

Research team member at KaiLab, specializing in Kurdish language technology and computational linguistics.

Researcher in natural language processing and machine translation.

Researcher and coauthor of work on handwritten Sorani Kurdish text recognition and the DASNUS dataset.

Co-author of Central Kurdish neural speech-synthesis research and creator of the SoraniTTS speech corpus.

Researcher and coauthor of work on lexical gaps in English-Kurdish scientific translation.

Researcher contributing to verified Kurdish language-resource research.

Coauthor of the Kurdish Standard EMNIST-like character dataset publication.

Researcher in Kurdish speech and language technology associated with the University of Tehran. Co-author of Jira and multiple Central and Northern Kurdish automatic speech recognition studies.

Co-author of research adapting F5-TTS for Sorani Kurdish speech synthesis.

Lead author of the Kurdish Standard EMNIST-like character dataset publication.

Author of verified Kurdish spelling-correction research included in this project.

Researcher and co-author of Central Kurdish text-to-speech research and the Gigant-KTTS speech corpus.

Researcher and co-author of Jira, the Central Kurdish speech recognition system and associated speech-resource work.

Coauthor of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Author of the 2026 Garrusi Kurdish study evaluating unadapted multilingual automatic speech recognition using staged normalization.

Researcher in Kurdish language technology associated with the University of Kurdistan Hewlêr. Co-author of early Sorani Kurdish speech-to-text research and other Kurdish language-processing studies.

Researcher and coauthor of KSTRV1, a scene-text recognition dataset involving Central Kurdish.

Researcher and coauthor of work on translating medical terminology into Kurdish.

Researcher contributing to verified Kurdish language-resource research.

Co-author of verified Kurdish-English machine translation research.

Researcher associated with LIUM at Le Mans Université and contributor to Southern Kurdish speech-recognition resources and benchmarking.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher contributing to verified Kurdish language-resource research.

Researcher contributing to verified Kurdish language-resource research.

Co-author of research on Central Kurdish text-to-speech and speech-to-text translation, including the TTS4All Central Kurdish speech resources.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher in Kurdish speech technology and language resources. Contributor to Jira and later Kurdish speech-resource and ASR research covering Central, Southern, and Northern Kurdish.

Coauthor of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Author of verified Kurdish spelling-correction research included in this project.

Researcher and coauthor of work on translating medical terminology into Kurdish.

Research team responsible for the No Language Left Behind multilingual machine translation project.

Co-author of verified research comparing allophone-, syllable-, and diphone-based text-to-speech systems for Kurdish.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher and lead author of the K-PIT and K-ZHMARA Kurdish handwriting dataset publication.

Researcher and coauthor of a published dataset of handwritten Central Kurdish isolated characters.

Author of verified Kurdish spelling-correction research included in this project.

Coauthor of the Kurdish Standard EMNIST-like character dataset publication.

Researcher at the University of Kurdistan Hewlêr whose work includes automatic text summarization of Sorani Kurdish research documents.

Author of verified Kurdish spelling-correction research included in this project.

Researcher contributing to verified Kurdish language-resource research.

Co-author of the 2022 Central Kurdish text-to-speech transfer-learning study included in this collection.

Researcher and co-author of Central Kurdish neural text-to-speech studies using Tacotron 2, transfer learning, and neural vocoding.

Co-author of Transformer-enhanced deep-learning research for Central Kurdish text-to-speech synthesis. The associated paper PDF spells the surname Ahmed.

Researcher and coauthor of verified work on printed Sorani Kurdish OCR using Tesseract LSTM.

Researcher contributing to verified Kurdish language-resource research.

Researcher and coauthor of KSTRV1, a scene-text recognition dataset involving Central Kurdish.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Coauthor of published research on handwritten Central Kurdish character data.

Researcher contributing to verified Kurdish language-resource research.

Researcher and co-author of the Transformer-based Northern Kurdish automatic speech recognition study using Whisper.

Researcher contributing to verified Kurdish language-resource research.

Researcher in Kurdish natural language processing and creator of KurdSum, a benchmark dataset for Kurdish text summarization.

Co-author of Transformer-enhanced deep-learning research for Central Kurdish text-to-speech synthesis.

Researcher and coauthor of work on terminology and the Kurdish lexicon.

Researcher at the University of Kurdistan Hewlêr working in artificial intelligence, machine learning, optimization, and Kurdish language and speech technology. Co-author of Transformer-based Central and Northern Kurdish ASR research.

Researcher and coauthor of work on language conventions in Kurdish scientific books.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Co-author of verified research comparing allophone-, syllable-, and diphone-based text-to-speech systems for Kurdish.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher and co-author of Jira, the Central Kurdish speech recognition system and associated resource-development study.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Researcher contributing to verified Kurdish language-resource research.

Co-author of the Massively Multilingual Speech research covering speech technology for more than one thousand languages.

Author of verified research discussing scientific terminology in Kurdish.