AISPEECH-SJTU口音识别系统用于口音英语语音识别挑战赛
AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
摘要：
本文介绍了用于Interspeech-2020重音英语语音识别挑战赛重音识别赛道的AISpeech-SJTU系统。在这个挑战轨道中，只提供了从8个国家收集的160小时带口音的英语数据和辅助的Librisepeech数据集用于训练。为了建立一个准确和鲁棒的口音识别系统，我们详细探讨了整个系统的流水线。首先，我们引入了基于语音识别的音素后验图（PPG）特征来进行口音识别，并验证了其有效性。然后，一种新的TTS为基础的方法是精心设计的，以增加非常有限的口音训练数据的第一次。最后，我们提出了测试时间增强和嵌入融合方案，以进一步提高系统的性能。我们最终的系统在挑战赛中排名第一，并且以很大的优势超过了所有其他参与者。该系统在挑战性评估数据上的平均准确率达到83.63%，在绝对值上领先其他系统10%以上。
英文摘要：
This paper describes the AISpeech-SJTU system for the accent identification track of the Interspeech-2020 Accented English Speech Recognition Challenge. In this challenge track, only 160-hour accented English data collected from 8 countries and the auxiliary Librispeech dataset are provided for training. To build an accurate and robust accent identification system, we explore the whole system pipeline in detail. First, we introduce the ASR based phone posteriorgram (PPG) feature to accent identification and verify its efficacy. Then, a novel TTS based approach is carefully designed to augment the very limited accent training data for the first time. Finally, we propose the test time augmentation and embedding fusion schemes to further improve the system performance. Our final system is ranked first in the challenge and outperforms all the other participants by a large margin. The submitted system achieves 83.63\% average accuracy on the challenge evaluation data, ahead of the others by more than 10\% in absolute terms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
