Deep-learning based Speech Recognition Technology 

Technology Summary

• 'Deep-learning based speech recognition technology' is a high-performance natural language speech recognition technology targeting various mobile environments (including smartphones, automobiles, and AI speakers), customer care centers (including call centers based on wired, wireless telephones, online and offline), and various speech records (including meeting, announcement, conference, broadcasting, etc.).
  
• Using this natural language speech recognition technology, it is possible to develop a speech-to-text(STT) conversion service and system for various speech records.
  
• It is possible to enhance the customers’ satisfaction by searching for desired information or responding quickly to customers.

Contact Info.: Su-Jin Youn, +82-42-860-5092, sjy@etri.re.kr