Joint Estimation of Articulatory Features and Acoustic models for Low-Resource Languages

Using articulatory features for speech recognition improves the performance of low-resource languages. One way to obtain articulatory features is by using an articulatory classifier (pseudo articulatory features). The performance of the articulatory features depends on the efficacy of this classifier. But, training such a robust classifier for a low-resource language is constrained due to the limited amount of training data. We can overcome this by training the articulatory classifier using a high resource language. This classifier can then he used to generate articulatory features for the low-resource language. However, this technique fails when high and low-resource languages have mismatches in their environmental conditions. In this paper, we address both the aforementioned problems by jointly estimating the articulatory features and low-resource acoustic model. The experiments were performed on two low-resource Indian languages namely, Hindi and Tamil. English was used as the high-resource language. A relative improvement of 23% and 10% were obtained for Hindi and Tamil, respectively.