Automatic Speech Recognition (ASR)

Voice recognition technology for Kurdish dialects and spoken language processing

Active
Started: March 2022
3 Team Members

Project Overview

Comprehensive ASR system supporting all major Kurdish dialects with advanced domain adaptation techniques. Our research addresses acoustic modeling challenges unique to Kurdish phonology and achieves state-of-the-art performance on conversational speech recognition.

Technologies & Methods

Deep Neural Networks Acoustic Modeling Language Modeling Domain Adaptation

Applications

  • Voice Assistants
  • Accessibility Tools
  • Transcription Services

Related Publications

Automatic Speech Recognition for Kurdish Dialects

Dr. Mohammad Ali , Dr. John Doe , Dr. Sara Ahmed (2023)

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 …

Related Datasets

Kurdish Speech Recognition Audio Corpus

Published: August 2, 2023 | Size: 12.5 GB

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

Published: March 30, 2023 | Size: 120 MB

Comprehensive pronunciation dictionary for Kurdish containing phonetic transcriptions for 75,000 words, including stress patterns and dialectal variations using IPA notation.

Project Statistics

Publications: 1
Datasets: 2
Team Size: 3

Research Team

Funding

International Speech Technology Research Initiative