Comprehending Real Numbers: Development of Bengali Real Number Speech Corpus
This addresses the problem of limited speech recognition resources for Bengali speakers, though it is incremental as it focuses on a specific numeric domain.
The authors tackled the lack of a comprehensive Bengali speech dataset by developing the first Bengali speech corpus for real numbers, comprising over 2,000 samples from 10 speakers totaling nearly 4 hours, and evaluated two existing Bengali speech recognizers on it.
Speech recognition has received a less attention in Bengali literature due to the lack of a comprehensive dataset. In this paper, we describe the development process of the first comprehensive Bengali speech dataset on real numbers. It comprehends all the possible words that may arise in uttering any Bengali real number. The corpus has ten speakers from the different regions of Bengali native people. It comprises of more than two thousands of speech samples in a total duration of closed to four hours. We also provide a deep analysis of our corpus, highlight some of the notable features of it, and finally evaluate the performances of two of the notable Bengali speech recognizers on it.