Home>Technology>Speech Recognition

Speech Recognition

What is Speech Synthesis? The technology黴€to convert text into human voice.

Feature

  • Three system choices depending on costumer’s need: distributed model (DSR), local model (LSR) and hybrid model.
  • ATR noise reduction technology for non-stationary noise.
  • Acoustic model generated from large speech data, collected from a number of services.
  • Large vocabulary language model using sentence data collected from various fields.
  • State-of-the-art speech recognition engine developed by our joint research.
  • Supported language: Japanese, Chinese and English. Indonesian and Korean are under development.

Our Japanese speech recognition technology is used in “vGate ASR” by FueTrek.
More information for “about the speech recognition technology”(Directed to FueTrek website)

  • “vGate” uses the speech recognition technology developed by ATR-Trek,based on Advanced Telecommunications Research Institute International (ATR) and National Institute of Information and Communications Technology (NICT)’s technology.
  • “vGate ASR” is a registered trademark of FueTrek Co., Ltd.
  • ATR-Trek speech recognition technology has been developed based on Advanced Telecommunications Research Institute International (ATR) and National Institute of Information and Communications Technology (NICT)’s technology.
  • Other names may be trademarks of their respective owners.