Speech recognition - a technology that can identify spoken words and convert them into text - is now widely used by some of the biggest tech companies around the world. However, while speech recognition for some languages such as English has been developed for a long time and reached an accuracy rate as high as 99%, speech recognition for the Vietnamese language is still in its infancy, with only a handful of companies providing such services.

To promote the utilization of speech recognition technology for the Vietnamese language, ADAI Lab has been researching and developing its own speech recognition solution. Building on the Speech-to-text API powered by Google's AI technologies, we hope to create a software that can not only accurately transcribe spoken Vietnamese, but also recognize the intricacies in pitches, tones, and regional accents.

We aim to provide this software for both military and civilian uses, which include:

• Securely transcribe strategic meetings in real time
• Use speech recognition in conjunction with other business applications (smart speaker, mobile apps, etc.)