Communication support system using speech recognition technology and speech synthesis technology

Abstract

The present disclosure relates to a system that converts a user's voice into another language in real time and outputs it with a voice that maintains individuality. A voice input unit captures voice using a high-sensitivity microphone and removes noise with noise canceling technology. A speech recognition unit operates on the cloud and converts voice into text using an acoustic model and a language model. A translation unit translates text into another language using neural machine translation technology and considers context and cultural nuances. A speech synthesis unit selects a voice close to the user's voice quality from a voice database and generates a natural and unique voice. A voice output unit uses low-latency technology to transmit the synthesized voice to the user in real time.

Dependencies are inferred from the claim text.