Automatic recognition of Slovak-English bilingual speech

This article describes the progress of a joint project on Multilingual Automatic Speech Recognition using Deep Neural Networks, in which the Technical University works together with National Taipei University of Technology in Taiwan. During the last year, we managed to train multilingual models of combinations of Slovak - English and Slovak - English - Chinese/Mandarin languages. In this paper, we are presenting the results of the Slovak - English model based on deep learning with and without language detection. Furthermore we present new bilingual Slovak-English code-switching database for bilingual systems training and testing. The results indicate that the use of the language detection module can lower the error rate of the multilingual model to the result similar to monolingual models that are generally better for the monolingual tasks.