CNN-Based Speaker Verification and Speech Recognition in Tibetan. (December 2020)

• Record Type: Journal Article
• Authors: Gan, Zhenye; Yu, Yue; Wang, Rui; Zhao, Xin
• Is Part Of: Journal of physics. Volume 1693(2020)
• Publication Date: 2020-12
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1693/1/012180
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In recent years, there have a little studies on speaker and speech recognition in Tibetan, which are mainly based on traditional methods of probability statistics. With the development of deep learning, neural networks have been widely used in speaker and automatic speech recognition, which have achieved remarkable results. In this paper, we utilize end-to-end model to study speaker verification and speech recognition in Tibetan. This article uses the ResCNN network for Tibetan speaker verification. In speech recognition, we adopt the DFCNN-CTC structure, where connectionist temporal classification (CTC) directly outputs the probability of sequence prediction without external post-processing. We have made some improvements to the two models. Experiments show that the improved model reduces EER by 3% and WER by 18% in speaker verification and speech recognition, respectively.