Professor Keiichi Tokuda
My research focuses on speech recognition and speech synthesis. It has recently become possible to search for information using voice recognition instead of interfaces using keyboards and displays. This is because oral communication is more natural, and the task of typing information with the keyboard is becoming difficult due to the miniaturization of devices. In addition, the audio interface has the advantage of being advantageous to a wide range of ages. Furthermore, compared to other interfaces, voice technology is also being considered for automated driving due to its safety. Numerous audio technologies developed based on over 20 years of research experience are released in open source and used in various new products of companies. In recent years, there has been a dramatic increase in technical demand for voice technology development, and joint research with universities and research institutes as well as major IT companies aiming at commercialization is thriving. In the future, we are proceeding with development so that synthesized speech will become more expressive and will enable human-like dialogue.
Link to Laboratory Website
Copyright© NITech Frontier Research Institutes, Inc. All Rights Reserved.