Abstract
We present VinAI Translate-a system that integrates state-of-the-art deep learning technologies in speech and natural language processing to translate speech and text between Vietnamese and English. Experimental results show that our system obtains a state-of-the-art performance for each translation direction, and outperforms Google Translate in both automatic and human evaluations.
Original language | English |
---|---|
Title of host publication | Interspeech 2022 |
Editors | Hanseok Ko, John H. L. Hansen |
Place of Publication | Baixas FRANCE |
Publisher | International Speech Communication Association (ISCA) |
Pages | 5543-5544 |
Number of pages | 2 |
Publication status | Published - 2022 |
Externally published | Yes |
Event | Annual Conference of the International Speech Communication Association (was Eurospeech) 2022 - Incheon, Korea, South Duration: 18 Sept 2022 → 22 Sept 2022 Conference number: 23rd https://www.isca-speech.org/archive/interspeech_2022/index.html (Proceedings) |
Publication series
Name | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
---|---|
Publisher | ISCA |
Volume | 2022-September |
ISSN (Print) | 2308-457X |
Conference
Conference | Annual Conference of the International Speech Communication Association (was Eurospeech) 2022 |
---|---|
Abbreviated title | INTERSPEECH 2022 |
Country/Territory | Korea, South |
City | Incheon |
Period | 18/09/22 → 22/09/22 |
Internet address |
Keywords
- Automatic speech recognition
- English
- Machine translation
- Text-to-speech
- Vietnamese