The CUHK-TUDELFT System for The SLT 2021 Children Speech Recognition Challenge
Si Ioi Ng, Wei Liu, Zhiyuan Peng, Siyuan Feng, Hing-Pang Huang, Odette Scharenborg, Tan Lee · arXiv (Cornell University) · 2020
This technical report describes our submission to the 2021 SLT Children Speech Recognition Challenge (CSRC) Track 1. Our approach combines the use of a joint CTC-attention end-to-end (E2E) speech recognition framework, transfer learning, data augmentation and development of various language models. Procedures of data pre-processing, the background and the course of system development are described. The analysis of the experiment results, as well as the comparison between the E2E and DNN-HMM hybrid system are discussed in detail. Our system achieved a character error rate (CER) of 20.1% in our designated test set, and 23.6% in the official evaluation set, which is placed at 10-th overall.