Asosiy kontentga oʻtish
Boshqa

USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments

Hüseyin Atakan VarolComputer Systems, Tashkent University of Information Technology named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanMannon OchilovInstitute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, KazakhstanYerbolat KhassanovComputer Systems, Tashkent University of Information Technology named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanIlyos KhujayorovInstitute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, KazakhstanSaida MussakhojayevaComputer Systems, Tashkent University of Information Technology named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanMuhammadjon MusaevInstitute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Nur-Sultan, Kazakhstan
2021en
ABI

Annotatsiya

We present a freely available speech corpus for the Uzbek language and report preliminary automatic speech recognition (ASR) results using both the deep neural network hidden Markov model (DNN-HMM) and end-to-end (E2E) architectures. The Uzbek speech corpus (USC) comprises 958 different speakers with a total of 105 h of transcribed audio recordings. To the best of our knowledge, this is the first open-source Uzbek speech corpus dedicated to the ASR task. To ensure high quality, the USC has been manually checked by native speakers. We first describe the design and development procedures of the USC, and then explain the conducted ASR experiments in detail. The experimental results demonstrate promising results for the applicability of the USC for ASR. Specifically, 18.1% and 17.4% word error rates were achieved on the validation and test sets, respectively. To enable experiment reproducibility, we share the USC dataset, pre-trained models, and training recipes in our GitHub repository (https://github.com/IS2AI/Uzbek_ASR).

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar