Abstract: Certain systems can function well only if they recognize the sound environment as humans do. In this research, we focus on sound classification by adopting a convolutional neural network and aim to develop a method that automatically classifies various environmental sounds. Although the neural network is a powerful technique, the performance depends on the type of input data. Therefore, we propose an approach via a slice bispectrogram, which is a third-order spectrogram and is a slice version of the amplitude for the short-time bispectrum. This paper explains the slice bispectrogram and discusses the effectiveness of the derived method by evaluating the experimental results using the ESC‑50 sound dataset. As a result, the proposed scheme gives high accuracy and stability. Furthermore, some relationship between the accuracy and non-Gaussianity of sound signals was confirmed.
Abstract: To develop the useful acoustic environmental
recognition system, the method of estimating 3D-position of a
stationary random acoustic source using bispectral analysis of
4-point detected signals is proposed. The method uses information
about amplitude attenuation and propagation delay extracted from
amplitude ratios and angles of auto- and cross-bispectra of the
detected signals. It is expected that using bispectral analysis affects
less influence of Gaussian noises than using conventional power
spectral one. In this paper, the basic principle of the method is
mentioned first, and its validity and features are considered from
results of the fundamental experiments assumed ideal circumstances.