论文标题
SLT 2021儿童语音识别挑战的Cuhk-Tudelft系统
The CUHK-TUDELFT System for The SLT 2021 Children Speech Recognition Challenge
论文作者
论文摘要
该技术报告描述了我们对2021 SLT儿童语音识别挑战（CSRC）曲目1的提交。我们的方法结合了使用联合CTC主管端到端（E2E）语音识别框架，转移学习，数据增强和各种语言模型的发展。描述了数据预处理，背景和系统开发过程的过程。详细讨论了实验结果的分析以及E2E和DNN-HMM混合系统之间的比较。我们的系统在我们指定的测试集中达到了20.1％的字符错误率（CER），在官方评估集中达到了23.6％，总体排名为10-10。
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.
