Projects per year
Abstract
A lot of research aims to improve accuracy in end-to-end speech recognition, and achieves higher accuracy on various famous corpora. However, there are many languages which do not have enough data to build their speech recognition system in the world. The system often cannot get a reliable result and be used in the real-world. Therefore, how to build a robust low-resource speech recognition system is an important issue in speech recognition. In this paper, we use ESPnet toolkit to implement an end-to-end speech recognition model based on sequence-to-sequence architecture, and use Fairseq toolkit to implement an unsupervised pre-training model for assisted speech recognition. In addition, we use unlabeled speech data to help extract speech features, and transfer a speech recognition model with sufficient corpus to Hakka speech recognition with less corpus through transfer learning. Experimental results show that we establish a more robust low-resource Hakka speech recognition system.
Original language | English |
---|---|
Title of host publication | Proceedings - 2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022 |
Editors | Vo Nguyen Quoc Bao, Tran Manh Ha |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 145-149 |
Number of pages | 5 |
ISBN (Electronic) | 9781665461665 |
DOIs | |
State | Published - 2022 |
Event | 2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022 - Ho Chi Minh City, Viet Nam Duration: 20 Dec 2022 → 22 Dec 2022 |
Publication series
Name | Proceedings - 2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022 |
---|
Conference
Conference | 2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022 |
---|---|
Country/Territory | Viet Nam |
City | Ho Chi Minh City |
Period | 20/12/22 → 22/12/22 |
Keywords
- computational paralinguistics
- human-computer interaction
- speech recognition
Fingerprint
Dive into the research topics of 'Low-Resource Speech Recognition Based on Transfer Learning'. Together they form a unique fingerprint.Projects
- 3 Finished
-
-
-
Deep Intelligence Based Spoken Language Processing( III )
Wang, J.-C. (PI)
1/01/20 → 31/12/20
Project: Research