Multilingual Speech Recognition for Turkic Languages
Mussakhojayeva S. Dauletbek K. Yeshpanov R. Varol H.A.
February 2023MDPI
Information (Switzerland)
2023#14Issue 2
The primary aim of this study was to contribute to the development of multilingual automatic speech recognition for lower-resourced Turkic languages. Ten languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek—were considered. A total of 22 models were developed (13 monolingual and 9 multilingual). The multilingual models that were trained using joint speech data performed more robustly than the baseline monolingual models, with the best model achieving an average character and word error rate reduction of 56.7%/54.3%, respectively. The results of the experiment showed that character and word error rate reduction was more likely when multilingual models were trained with data from related Turkic languages than when they were developed using data from unrelated, non-Turkic languages, such as English and Russian. The study also presented an open-source Turkish speech corpus. The corpus contains 218.2 h of transcribed speech with 186,171 utterances and is the largest publicly available Turkish dataset of its kind. The datasets and codes used to train the models are available for download from our GitHub page.
automatic speech recognition , big data , Common Voice , Kazakh Speech Corpus , lower-resourced languages , multilingual speech recognition , transfer learning , Turkic languages , Turkish Speech Corpus , Uzbek Speech Corpus
Text of the article Перейти на текст статьи
Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Astana, 010000, Kazakhstan
Institute of Smart Systems and Artificial Intelligence (ISSAI)
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026