Bayesian Models for Unit Discovery on a Very Low Resource Language
This work addresses speech technology development for low-resource languages, though it is incremental as it applies existing Bayesian models to a new real-world scenario.
The authors tackled unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario using Bayesian models, showing that they outperform a Segmental-DTW baseline in word segmentation results.
Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are used, either as the 1-best sequence or as a lattice, to perform word segmentation. Word segmentation results show that this Bayesian approach clearly outperforms a Segmental-DTW baseline on the same corpus.