Automatic Speech Recognition for Kurdish Dialects
Authors
Speech Communication
Vol. 145
pp. 102-118
September 10, 2023
Member Organizations:
Abstract
This research develops the first comprehensive ASR system for Kurdish, supporting both Sorani and Kurmanji dialects with domain adaptation techniques. Achieved 89.3% word accuracy on conversational speech.
Keywords
ASR
Kurdish Dialects
Sorani
Kurmanji
Domain Adaptation
Related Datasets
Kurdish Speech Recognition Audio Corpus
August 2, 2023
12.5 GB
WAV, TXT, JSON, TextGrid
Large-scale audio corpus containing 1,000 hours of Kurdish speech from 500+ speakers across different dialects, ages, and regions. Includes high-quality transcriptions and speaker metadata.
Kurdish Phonetic Pronunciation Dictionary
March 30, 2023
120 MB
JSON, CSV, TXT
Comprehensive pronunciation dictionary for Kurdish containing phonetic transcriptions for 75,000 words, including stress patterns and dialectal variations using IPA notation.
Citation
Kareem, H., Ahmed, R., & Jamal, S. (2023). Automatic Speech Recognition for Kurdish Dialects. Speech Communication, 145, 102-118.