Acoustic Object Canceller Using Blind Compensation for Sampling Frequency Mismatch

Abstract

In this paper, we propose a method of removing a known interference from a monaural recording. Generally, the elimination of a nonstationary interference from a monaural recording is difficult. However, if it is a known sound, such as the ringtone of a cell phone, radio and TV broadcasts, and commercially available music provided by a CD or streaming, their signals can be easily obtained. In our proposed method, we define such interference as an acoustic object. Although the sampling frequencies of the recording and the available acoustic object might be mismatched, we compensate the mismatch and remove the acoustic object from the recording by maximum likelihood estimation using the auxiliary function technique. We confirm the effectiveness of our method by experimental evaluations.