Development of real-time noise reduction method for robot auditory utilizing speech recognition system

本研究针对机器人听觉系统中来自外部环境的噪声，提出了一种利用语音识别系统进行噪声抑制和参数调整的方法。本研究的特点不是单独对语音识别系统和降噪系统进行调优，而是对它们进行综合调优。通过将降噪系统与降噪系统集成，拓宽了参数整定的适用范围。它被认为是开发的系统将不仅适用于机器人的听觉，但也适用于汽车导航系统和生物识别。

In this study, we focus on noise reduction from external environment in robot auditory system, and developed noise reduction and parameter tuning method utilizing speech recognition system. The feature of this study is not to tune speech recognition system and noise reduction system independently, but to tune them in a comprehensive way. By integrating noise reduction system and noise reduction system totally, the applicable range of parameter tuning became wide. It is considered that the developed system will be applicable not only to robot auditory but also to car navigation system and biometric identification.