能動的音響制御を併用する低騒音な音声マスキング手法

抄録

The sound masking method is able to cover contents of conversation by using a masking sound. However, there is a problem that the sound level is increased because of a masking sound. Therefore, we suggested Low-noise sound masking method. In this method, spectrum of phonemes are made flat by using active noise control(ANC). It is difficult to recognize phonemes that are processed by this method because the major factor determining the phonemes in speech recognition is the relative relationship of the peaks of its spectrum. In this paper, we verify the control effect of the method by simulation.