Abstract—Speech Recognition is a widely studied topic for high-resource languages like English and Mandarin. A plethora of publications exist that study the performance of several recognition methods for these languages. However differences in phonetics, accent, language model, etc between any two different languages demand for a study of speech recognition methodologies and components separately for each language. In this paper, we present a comparative study of popular speech recognition methods for Nepali, a low-resource Indo-Aryan language. We describe our approach to building the phonetic dictionary and present our findings for DNN and GMM based techniques with speaker adaptation on 50K vocabulary speech recognition task. 

Index Terms—Nepali speech recognition, automatic speech recognition, Nepali speech processing, Nepali phonetic dictionary

Cite: Elina Baral and Sagar Shrestha, "Large Vocabulary Continuous Speech Recognition for Nepali Language," International Journal of Signal Processing Systems, Vol. 8, No. 4, pp. 68-73, December 2020. doi: 10.18178/ijsps.8.4.68-73