2D sound source position estimation using microphone arrays and its application to a VR-based bird song analysis system

Large-scale simulation of bird localization systems in forests with distributed microphone arrays

Acoustic wildlife monitoring systems are important tools for capturing information about animal habitation in ecosystems. Previous work has demonstrated the effectiveness of audio-based bird localization techniques. However, few studies have investigated the performance and robustness of distributed systems in large forests. Here, the performance of distributed microphone arrays for localizing birds is examined by simulating forest scenes with added reverberation, ambient noise, and measurement errors. The simulation revealed the importance of the signal-to-noise ratio and the spectral weighting in the localization algorithm. These results may guide the design of large-scale wildlife monitoring systems and suggest promising directions for further improvements.

Multichannel environmental sound segmentation

This paper proposes a multichannel environmental sound segmentation method. Environmental sound segmentation is an integrated method to achieve sound source localization, sound source separation and classification, simultaneously. When multiple microphones are available, spatial features can be used to improve the localization and separation accuracy of sounds from different directions; however, conventional methods have three drawbacks: (a) Sound source localization and sound source separation methods using spatial features and classification using spectral features trained in the same neural network, may overfit to the relationship between the direction of arrival and the class of a sound, thereby reducing their reliability to deal with novel events. (b) Although permutation invariant training used in autonomous speech recognition could be extended, it is impractical for environmental sounds that include an unlimited number of sound sources. (c) Various features, such as complex values of short time Fourier transform and interchannel phase differences have been used as spatial features, but no study has compared them. This paper proposes a multichannel environmental sound segmentation method comprising two discrete blocks, a sound source localization and separation block and a sound source separation and classification block. By separating the blocks, overfitting to the relationship between the direction of arrival and the class is avoided. Simulation experiments using created datasets including 75-class environmental sounds showed the root mean squared error of the proposed method was lower than that of conventional methods.

Assessment of Sound Source Tracking Using Multiple Drones Equipped with Multiple Microphone Arrays

Drone audition techniques are helpful for listening to target sound sources from the sky, which can be used for human searching tasks in disaster sites. Among many techniques required for drone audition, sound source tracking is an essential technique, and thus several tracking methods have been proposed. Authors have also proposed a sound source tracking method that utilizes multiple microphone arrays to obtain the likelihood distribution of the sound source locations. These methods have been demonstrated in benchmark experiments. However, the performance against various sound sources with different distances and signal-to-noise ratios (SNRs) has been less evaluated. Since drone audition often needs to listen to distant sound sources and the input acoustic signal generally has a low SNR due to drone noise, making a performance assessment against source distance and SNR is essential. Therefore, this paper presents a concrete evaluation of sound source tracking methods using numerical simulation, focusing on various source distances and SNRs. The simulated results captured how the tracking performance will change when the sound source distance and SNR change. The proposed approach based on location distribution estimation tended to be more robust against distance increase, while existing approaches based on directional estimation tended to be more robust against decreasing SNR.