Moklen, a tonal Austronesian language spoken in Thailand, exhibits two tones with unbalanced distributions. We employed machine learning techniques for time-series classification to investigate its acoustic properties. Our analysis reveals that a synergy between pitch and vowel quality is crucial for tone distinction, as the model trained with these features achieved the highest accuracy.
Leveraging deep learning to shed light on tones of an endangered language: A case study of Moklen
ChulaSEAL author(s):
APA: Maspong, S., Burroni, F., Sukanchanon, T., Pornpottanamas, W., & Pittayaporn, P. (2024, August). Leveraging Deep Learning to Shed Light on Tones of an Endangered Language: A Case Study of Moklen. In Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024) (pp. 37-42).
