• Home /
  • Papers /
  • Jira: a Central Kurdish speech recognition system, designing and building speech corpus and pronunciation lexicon

Abstract

Jira is a large-vocabulary speech recognition system for Central Kurdish (Sorani), developed together with a purpose-designed speech corpus and pronunciation lexicon. The work uses corpus design based on diphone distribution, acoustic modeling, and n-gram language modeling, reporting a word error rate of 13.9% on generic test items.

Keywords

Automatic Speech Recognition Central Kurdish Sorani Speech Corpus Pronunciation Lexicon

Related Datasets

AsoSoft Speech Corpus

2021 43.68 hours (full corpus); public subset approximately 30 hours Audio, Text Transcriptions

Central Kurdish (Sorani) speech corpus developed for automatic speech recognition and related speech-processing research. The full corpus reported in the Jira study contains 43.68 hours of speech from …

Citation

Veisi, H., Hosseini, H., MohammadAmini, M., Fathy, W., & Mahmudi, A. Jira: a Central Kurdish speech recognition system, designing and building speech corpus and pronunciation lexicon. Language Resources and Evaluation.

Publication Details

Authors 5 authors
Datasets 1 dataset