Neural networks

Although field-collected recordings typically contain multiple simultaneously vocalizing birds of different species, acoustic species classification in this setting has received little study so far. This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with MIML classifiers. The proposed representation uses a 2D time-frequency segmentation of the audio signal, which can separate bird sounds that overlap in time. Experiments using audio data containing 13 species collected with unattended omnidirectional microphones in the H. J. Andrews Experimental Forest demonstrate that the proposed methods achieve high accuracy (96.1% true positives/negatives). Automated detection of bird species occurrence using MIML has many potential applications, particularly in long-term monitoring of remote sites, species distribution modeling, and conservation planning.

https://www.fs.fed.us/pnw/pubs/journals/pnw_2012_briggs001.pdf

Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach

More than a third of elderly fall each year in the United States. It has been shown that the longer the lie on the floor, the poorer is the outcome of the medical intervention. To reduce delay of the medical intervention, we have developed an acoustic fall detection system (acoustic-FADE) that automatically detects a fall and reports it promptly to the caregiver. Acoustic-FADE consists of a circular microphone array that captures the sounds in a room. When a sound is detected, acoustic-FADE locates the source, enhances the signal, and classifies it as “fall” or “nonfall.” The sound source is located using the steered response power with phase transform technique, which has been shown to be robust under noisy environments and resilient to reverberation effects. Signal enhancement is performed by the beamforming technique based on the estimated sound source location. Height information is used to increase the specificity. The mel-frequency cepstral coefficient features computed from the enhanced signal are utilized in the classification process. We have evaluated the performance of acoustic-FADE using simulated fall and nonfall sounds performed by three stunt actors trained to behave like elderly under different environmental conditions. Using a dataset consisting of 120 falls and 120 nonfalls, the acoustic-FADE achieves 100% sensitivity at a specificity of 97%.

A Microphone Array System for Automatic Fall Detection

In real-world applications such as those for speech and audio, there are signals that are nonstationary but can be modeled as being stationary within local time frames. Such signals are generally called quasi-stationary or locally stationary signals. This paper considers the problem of direction-of-arrival (DOA) estimation of quasi-stationary signals. Specifically, in our problem formulation we assume: i) sensor array of uniform linear structure; ii) mutually uncorrelated wide-sense quasi-stationary source signals; and iii) wide-sense stationary noise process with unknown, possibly nonwhite, spatial covariance. Under the assumptions above and by judiciously examining the structures of local second-order statistics (SOSs), we develop a Khatri-Rao (KR) subspace approach that has two notable advantages. First, through an identifiability analysis, it is proven that this KR subspace approach can operate even when the number of sensors is about half of the number of sources. The idea behind is to make use of a ?virtual? array structure provided inherently in the local SOS model, of which the degree of freedom is about twice of that of the physical array. Second, the KR formulation naturally provides a simple yet effective way of eliminating the unknown spatial noise covariance from the signal SOSs. Extensive simulation results are provided to demonstrate the effectiveness of the KR subspace approach under various situations.

DOA Estimation of Quasi-Stationary Signals With Less Sensors Than Sources and Unknown Spatial Noise Covariance: A Khatri–Rao Subspace Approach

There is a great need for increased use and further development of automated sound recording and analysis of avian sounds. Birds are critical to ecosystem functioning so techniques to make avian monitoring more efficient and accurate will greatly benefit science and conservation efforts. We provide an overview of the hardware approaches to automated sound recording as well as an overview of the prominent techniques used in software to automatically detect and classify avian sound. We provide a comparative summary of examples of three general categories of hardware solutions for automating sound recording which include a hardware interface for a scheduling timer to control a standalone commercial recorder, a programmable recording device, and a single board computer. We also describe examples of the two main approaches to improving microphone performance for automated recorders through small arrays of microphone elements and using waveguides. For the purposes of thinking about automated sound analysis, we suggest five basic sound fragment types of avian sound and discuss a variety of techniques to automatically detect and classify avian sounds to species level, as well as their limitations. A variety of the features to measure for the various call types are provided, along with a variety of classification methods for those features. They are discussed in context of general performance as well as the monitoring and conservation efforts they are used in.

/pdf/automated-sound-recording-and-analysis-techniques-for-bird-4tusdmvt5g.pdf

Automated sound recording and analysis techniques for bird surveys and conservation

This paper presents a novel bird monitoring and recognition system in noisy environments. The project objective is to avoid bird strikes to aircraft. First, a cost-effective microphone dish concept (microphone array with many concentric rings) is presented that can provide directional and accurate acquisition of bird sounds and can simultaneously pick up bird sounds from different directions. Second, direction-of-arrival (DOA) and beamforming algorithms have been developed for the circular array. Third, an efficient recognition algorithm is proposed which uses Gaussian mixture models (GMMs). The overall system is suitable for monitoring and recognition for a large number of birds. Fourth, a hardware prototype has been built and initial experiments demonstrated that the array can acquire and classify birds accurately.

/pdf/an-automated-acoustic-systemto-monitor-and-classify-birds-4nqyfdo1y7.pdf

An automated acoustic systemto monitor and classify birds

To minimize the number of birdstrikes, a common method is to use microphone arrays to monitor and identify dangerous birds near the airport or some critical locations in the airspace. However, it was recognized that the range of existing ground-based acoustic monitoring devices is only limited to a few hundred meters. Moreover, the bird classification performance in low signal-to-noise environments such as airports is not very satisfactory. This paper summarizes the development of a high performance bird classification system using a hidden Markov model (HMM) and Gaussian mixture model (GMM). Experimental results verified the classification performance.

Bird classification algorithms: theory and experimental results

This paper summarizes our research and development effort on the investigation of an innovative approach to making a smart meeting room accessible to hands-free users with special needs. More specifically, we developed a real time system which is able to acquire speech from a privileged speaker at a distance across a noisy room, using a microphone array, and identify the speech signals from the privileged speaker, among others, in real time. We were successful in achieving this goal, and established that we can use commercially available speaker dependent speech recognition products to determine what the privileged speaker said, while simultaneously rejecting speech from other meeting attendees. To accomplish this goal, we implemented a real time speaker verification algorithm, based on Gaussian mixture models (GMM) commonly employed in speaker identification research. We used the smart flow system, developed by the National Institute of Standards and Technology (NIST), to conduct our experiments.

G. Mei

Papers

An automated acoustic systemto monitor and classify birds

Bird classification algorithms: theory and experimental results

A real time speaker verification demonstration on the smart flow system