Research Article


DOI :10.26650/acin.1338604   IUP :10.26650/acin.1338604    Full Text (PDF)

Transformer-Based Turkish Automatic Speech Recognition

Davut Emre TaşarKutan KoruyanCihan Çılgın

Today, businesses use Automatic Speech Recognition (ASR) technology more frequently to increase efficiency and productivity while performing many business functions. Due to the increased prevalence of online meetings in remote working and learning environments after the COVID-19 pandemic, speech recognition systems have seen more frequent utilization, exhibiting the significance of these systems. While English, Spanish or French languages have a lot of labeled data, there is very little labeled data for the Turkish language. This directly affects the accuracy of the ASR system negatively. Therefore, this study utilizes unlabeled audio data by learning general data representations with self-supervised learning end-to-end modeling. This study employed a transformer-based machine learning model with improved performance through transfer learning to convert speech recordings to text. The model adopted within the scope of the study is the Wav2Vec 2.0 architecture, which masks the audio inputs and solves the related task. The XLSR-Wav2Vec 2.0 model was pre-trained on speech data in 53 languages and fine-tuned with the Mozilla Common Voice Turkish data set. According to the empirical results obtained within the scope of the study, a 0.23 word error rate was reached in the test set of the same data set.


PDF View

References

Citations

Copy and paste a formatted citation or use one of the options to export in your chosen format


EXPORT



APA

Taşar, D.E., Koruyan, K., & Çılgın, C. (2019). Transformer-Based Turkish Automatic Speech Recognition. Acta Infologica, 0(0), -. https://doi.org/10.26650/acin.1338604


AMA

Taşar D E, Koruyan K, Çılgın C. Transformer-Based Turkish Automatic Speech Recognition. Acta Infologica. 2019;0(0):-. https://doi.org/10.26650/acin.1338604


ABNT

Taşar, D.E.; Koruyan, K.; Çılgın, C. Transformer-Based Turkish Automatic Speech Recognition. Acta Infologica, [Publisher Location], v. 0, n. 0, p. -, 2019.


Chicago: Author-Date Style

Taşar, Davut Emre, and Kutan Koruyan and Cihan Çılgın. 2019. “Transformer-Based Turkish Automatic Speech Recognition.” Acta Infologica 0, no. 0: -. https://doi.org/10.26650/acin.1338604


Chicago: Humanities Style

Taşar, Davut Emre, and Kutan Koruyan and Cihan Çılgın. Transformer-Based Turkish Automatic Speech Recognition.” Acta Infologica 0, no. 0 (Apr. 2024): -. https://doi.org/10.26650/acin.1338604


Harvard: Australian Style

Taşar, DE & Koruyan, K & Çılgın, C 2019, 'Transformer-Based Turkish Automatic Speech Recognition', Acta Infologica, vol. 0, no. 0, pp. -, viewed 23 Apr. 2024, https://doi.org/10.26650/acin.1338604


Harvard: Author-Date Style

Taşar, D.E. and Koruyan, K. and Çılgın, C. (2019) ‘Transformer-Based Turkish Automatic Speech Recognition’, Acta Infologica, 0(0), pp. -. https://doi.org/10.26650/acin.1338604 (23 Apr. 2024).


MLA

Taşar, Davut Emre, and Kutan Koruyan and Cihan Çılgın. Transformer-Based Turkish Automatic Speech Recognition.” Acta Infologica, vol. 0, no. 0, 2019, pp. -. [Database Container], https://doi.org/10.26650/acin.1338604


Vancouver

Taşar DE, Koruyan K, Çılgın C. Transformer-Based Turkish Automatic Speech Recognition. Acta Infologica [Internet]. 23 Apr. 2024 [cited 23 Apr. 2024];0(0):-. Available from: https://doi.org/10.26650/acin.1338604 doi: 10.26650/acin.1338604


ISNAD

Taşar, DavutEmre - Koruyan, Kutan - Çılgın, Cihan. Transformer-Based Turkish Automatic Speech Recognition”. Acta Infologica 0/0 (Apr. 2024): -. https://doi.org/10.26650/acin.1338604



TIMELINE


Submitted06.08.2023
Accepted30.11.2023
Published Online29.02.2024

LICENCE


Attribution-NonCommercial (CC BY-NC)

This license lets others remix, tweak, and build upon your work non-commercially, and although their new works must also acknowledge you and be non-commercial, they don’t have to license their derivative works on the same terms.


SHARE




Istanbul University Press aims to contribute to the dissemination of ever growing scientific knowledge through publication of high quality scientific journals and books in accordance with the international publishing standards and ethics. Istanbul University Press follows an open access, non-commercial, scholarly publishing.