Karakalpak speech corpus: the first benchmark dataset for automatic speech recognition

Kudaybergenov, Tangirbergen, Uteuliev, Niyetbay, Khudaybergenov, Kabul, Kudaybergenov, Jabbar

Al-Farg'oniy avlodlari · 2026-yil

Annotatsiya

While large-scale pre-trained models have significantly advanced multilingual Automatic Speech Recognition (ASR), many low-resource languages remain under-served due to the scarcity of high-quality annotated speech corpora. This paper introduces the Karakalpak Speech Corpus (KSC), the first publicly available benchmark dataset for Karakalpak, a Turkic language spoken by over two million people primarily in Karakalpakstan. The corpus encompasses 50 hours of predominantly read speech. The data was collected from 25 native speakers with a balanced gender distribution. To establish a performance benchmark, we fine-tuned the Wav2Vec 2.0 architecture, specifically evaluating the efficacy of transfer learning from multilingual pre-trained models

Maqola ma’lumotlari
MualliflarKudaybergenov, Tangirbergen, Uteuliev, Niyetbay, Khudaybergenov, Kabul, Kudaybergenov, Jabbar
JurnalAl-Farg'oniy avlodlari
NashriyotТАТУ Фарғона филиали
ISSN2181-4252
Nashr sanasi2026-03-18
Son1
Betlar262-269
TilIngliz
Ilmiy sohaTexnika
Indeksga qo‘shilgan2026-08-26

Maqolaning asl sahifasi

Kalit so‘zlar

speech dataset, speech recognition, speech-to-text, Transfer Learning, Wav2Vec 2.0 model, Machine Learning, Deep Learning

Ilmiy soha

Texnika

Iqtibos keltirish

APAKudaybergenov, Tangirbergen, Uteuliev, Niyetbay, Khudaybergenov, Kabul, & Kudaybergenov, Jabbar (2026). KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION. Al-Farg'oniy avlodlari, (1), 262-269. https://al-fargoniy.uz/index.php/journal/article/view/1079
GOST (OAK)Kudaybergenov, Tangirbergen va b. KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION // Al-Farg'oniy avlodlari. – 2026. – № 1. – P. 262-269.
MLAKudaybergenov, Tangirbergen, Uteuliev, Niyetbay, Khudaybergenov, Kabul, and Kudaybergenov, Jabbar. “KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION.” Al-Farg'oniy avlodlari, (1), 262-269, 2026. https://al-fargoniy.uz/index.php/journal/article/view/1079
ChicagoKudaybergenov, Tangirbergen, Uteuliev, Niyetbay, Khudaybergenov, Kabul, and Kudaybergenov, Jabbar. “KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION.” Al-Farg'oniy avlodlari, (1), 262-269 (2026). https://al-fargoniy.uz/index.php/journal/article/view/1079
HarvardKudaybergenov, Tangirbergen, Uteuliev, Niyetbay, Khudaybergenov, Kabul, and Kudaybergenov, Jabbar (2026) ‘KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION’, Al-Farg'oniy avlodlari, (1), 262-269. https://al-fargoniy.uz/index.php/journal/article/view/1079
BibTeX
@article{kudaybergenovtangirbergen2026,
  title = {KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION},
  author = {Kudaybergenov, Tangirbergen and Uteuliev, Niyetbay and Khudaybergenov, Kabul and Kudaybergenov, Jabbar},
  journal = {Al-Farg'oniy avlodlari},
  year = {2026},
  number = {1},
  pages = {262-269},
  url = {https://al-fargoniy.uz/index.php/journal/article/view/1079}
}

Boshqa maqola uchun iqtibos tayyorlash

Al-Farg'oniy avlodlari jurnalidan boshqa maqolalar

Al-Farg'oniy avlodlari — barcha maqolalar · 2026-yil arxivi

Texnika sohasidagi boshqa maqolalar

Texnika sohasidagi OAK jurnallari