I. Introduction
Respiration is one of major vital signs that reflect our health condition [1] [2]. Hence, demands for the respiration rate estimation in indoor environments have increased in various fields, e.g., health care and smart home. To monitor our health condition in our daily life, it is better to estimate the respiration rate without any wearable devices such as respiration belt, since the device attachment is not preferred in real application. In addition, it is demanded to estimate the respiration rate even in indoor environments where a subject is not right in front of the measurement device.