Tao Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tao Li has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Dexin Liao
School of Informatics, Xiamen University, Xiamen 361005, China
1 shared publication - Fuchuan Tong
School of Information Science and Engineering
1 shared publication - Lin Li
School of Electronic Science and Engineering, Xiamen University, Xiamen 361100, China
1 shared publication - Qingyang Hong
School of Informatics, Xiamen University, Xiamen, China
1 shared publication - Shipeng Xia
School of Informatics, Xiamen University, Xiamen 361005, China
1 shared publication - Song Li
School of Electronic Science and Engineering, Xiamen University, Xiamen 361005, China
1 shared publication
Latest Publications
- Open Access
- 29 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1478
The XMUSPEECH System for Accented English Automatic Speech Recognition
In this paper, we present the XMUSPEECH systems for Track 2 of the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC2020). Track 2 is an Automatic Speech Recognition (ASR) task where the non-native English speakers have various accents, which reduces the accuracy of the ASR system. To solve this problem, we experimented with acoustic models and input features. Furthermore, we trained a TDNN-LSTM language model for lattice rescoring to obtain better results. Compared with our baseline system, we achieved relative word error rate (WER) improvements of 40.7% and 35.7% on the development set and evaluation set, respectively.
- 29 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1478
Open AccessThe XMUSPEECH System for Accented English Automatic Speech Recognition
In this paper, we present the XMUSPEECH systems for Track 2 of the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC2020). Track 2 is an Automatic Speech Recognition (ASR) task where the non-native English speakers have various accents, which reduces the accuracy of the ASR system. To solve this problem, we experimented with acoustic models and input features. Furthermore, we trained a TDNN-LSTM language model for lattice rescoring to obtain better results. Compared with our baseline system, we achieved relative word error rate (WER) improvements of 40.7% and 35.7% on the development set and evaluation set, respectively.