Voice Recognition Solutions (STT / Speech-to-Text)
- Our key technology with the ability to listen to the sounds of the world and analyze the meaning of these sounds to provide the most meaningful information.
- To provide a variety of voice recognition solutions, including keyword,
full-text, real-time and batch
- - ETRI voice recognition engine applied with Deep Neural Network (DNN) and high-speed noise processing technology
- - Application of the Recurrent Neural Network (RNN) algorithm to the pre-processing stage
- - The first in Korea to provide speaker/environmental high-speed, adaptive technology
- - Voice-interactive, unmanned counselling service through virtual agent interworks