Inteligencia Artificial para el análisis de la pronunciación de lenguas indígenas
Abstract
Language analysis is currently considered important for different researchers because there are people with the objective of learning a second language, scientists develop applications that provide feedback on texts or pronunciations made by learners, generating a score and a recommendation within the teaching process. Over time, languages considered universal such as English, Spanish, or Mandarin are considered to develop these applications due to their demand. However, in recent years other languages considered low resources due to their low appearance of data within a computational environment and the cases of speakers, have been considered with different objectives, preservation, semantic research, learning, among others, considering, among them, indigenous languages from around the world, being part of a cultural wealth within the regions that are spoken. The objective of this article is to present language as a form of communication that can consider computational aspects for this process, in addition to analyzing some applications used for teaching and learning another language, considering automatic voice recognition processes and the challenges that consider the analysis of indigenous languages of Mexico.
Downloads
References
Li, X., Dalmia, S., Li, J., Lee, M., Littell, P., Yao, J., y Metze, F. Universal phone recognition with a multilingual allophone system. ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.8249- 8253, 2020.
López, J. M. M., y Herrero, J. G. Técnicas de análisis de datos. Aplicaciones prácticas utilizando Microsoft Excel y weka, 2006.
Medina, J. d. (1999). Explicación y Análisis: Taller de Comunicación I. México: UNAM.
Mukhamadiyev, A., Khujayarov, I., Djuraev, O., y Cho, J. Automatic speech recognition method based on deep learning approaches for Uzbek language. Sensors, 22(10), 3683, 2022.
Penner, K. (2019). Prosodic structure in Ixtayutla Mixtec: Evidence for the foot.
Rajendran, S. M. (2021). Language dialect-based speech emotion recognition through deep learning techniques. International Journal of Speech Technology, 24(3), 625-635.
Yu, D., y Deng, L. Automatic speech recognition (Vol. 1). Berlin: Springer, 2016.