Khmer Automatic Speech Recognition – Khmer ASR

1. About technology

“Khmer Automatic Speech Recognition (Khmer ASR)” is a system that uses Artificial Intelligence technology to automatically convert speech and audio files in Khmer to text. . The system was developed entirely by a team of young researchers from the Academy of Digital Technology of Cambodia (formerly the National Institute of Posts, Telecommunications, Information and Communication Technology) of the Ministry of Posts and Telecommunications, using a combination of Statistical Learning and Deep methods. Learning, a new method for creating automated systems to convert speech into written text for complex and low-data languages ​​in digital form.

2. Benefits

This technology may allow the Cambodian technology research and development community to use or equip other systems or technologies for the following key tasks:

1. Facilitate and speed up the implementation of daily tasks, such as recording meetings and other programs that are not very noisy, such as the conversion of speech into written text, the conversion of teaching voice into written text in training work. Etc.

2. Equipped with technology to assist people with disabilities in their work and daily life.

3. Develop Voice Command technology in Khmer on objects and equipment.