Development of a Vietnamese speech recognition system for Viettel call center

摘要

In this paper, we first present our effort to collect a 85.8 hour corpus for Vietnamese telephone conversational speech from our Viettel call center. After that, various techniques such as time delay deep neural network (TDNN) with sequence training, data augmentation are applied to build the speech recognition system. Our final system achieves a low word error rate at 17.44% for this challenging corpus. To the best of our knowledge, it is the first attempt to build Vietnamese corpus and speech recognition system for the customer service domain.