Sound source tracking based on updating histogram
Takeshi Suzuki, Kenji Suyama · 2012
In this paper, a method for a single sound source tracking using a sequential updating histogram based on a speech sparseness by two microphones is proposed. The sound source localization based on the sequential updating histogram can estimate the direction-of-arrival even when a talker moves rapidly. In this paper, such a method is attempted to apply for the sound source tracking problem which the talker moves continuously. Several experiments were conducted in a noisy environment room to evaluate the effectiveness of the proposed method.