Blind speech extraction for Non-Audible Murmur speech with speaker's movement noise

In this paper, we address an improved method of noise reduction used in multichannel Non-Audible Murmur (NAM) based on blind source separation. Recently, speech processing with NAM has been proposed for applying versatile speech interface into quiet environments where we hesitate to utter. NAM is a very soft whispered voice signal detected with the NAM microphone, which is one of the body-conductive microphone. The detected NAM signal always suffers from nonstationary noise caused by speaker's movement because it changes the setting condition of the NAM microphone. In order to reduce the noise signal, blind noise reduction using stereo NAM signals detected with two NAM microphones has been proposed by some of the authors. In this paper, we aim to achieve further improvement in the noise reduction ability by changing the noise estimation and postprocessing algorithms to enhance the target NAM signal. In addition, we evaluate the application of recording the NAM signals with various types of microphones.