Monitoring and Mining Animal Sounds in Visual Space

Abstract

Monitoring animals by the sounds they produce is an important and challenging task, whether the application is outdoors in a natural habitat, or in the controlled environment of a laboratory setting.In the former case, the density and diversity of animal sounds can act as a measure of biodiversity. In the latter case, researchers often create control and treatment groups of animals, expose them to different interventions, and test for different outcomes. One possible manifestation of different outcomes may be changes in the bioacoustics of the animals.With such a plethora of important applications, there have been significant efforts to build bioacoustic classification tools. However, we argue that most current tools are severely limited. They often require the careful tuning of many parameters (and thus huge amounts of training data), are either too computationally expensive for deployment in resource-limited sensors, specialized for a very small group of species, or are simply not accurate enough to be useful.In this work we introduce a novel bioacoustic recognition/classification framework that mitigates or solves all of the above problems. We propose to classify animal sounds in the visual space, by treating the texture of their sonograms as an acoustic fingerprint using a recently introduced parameter-free texture measure as a distance measure. We further show that by searching for the most representative acoustic fingerprint, we can significantly outperform other techniques in terms of speed and accuracy.

Precise and Low-Cost Monitoring of Plum Curculio (Coleoptera: Curculionidae) Pest Activity in Pyramid Traps With Cameras

“…Furthermore, digital samples from insect populations have the potential to be examined and interpreted very rapidly via image recognition software. Although still in the early stages of development, digital systems are capable of identifying trapped insects to species via photographs (Larios et al 2008, Wen et al 2009) or sound recordings (Hao et al 2013), thereby potentially offering a method for automating the counting of trap collections and improving both species-speciÞc and overall arthropod biodiversity assessment. If focused on pests, these types of systems would complement the ongoing development of online and handheld device software designed to provide decision support to practitioners of IPM.…”

Acoustic detection of elephant presence in noisy environments

“…We compare the proposed approach with two baseline approaches: (i) the semi-supervised template-based approach by [7], short "B1" and (ii) call detection based on the GFCC features as proposed by [3], short "B2". Table 1 provides the performance measures of the baseline methods and the proposed approach (short "P").…”

“…To be fair, it must be said that the method does not take any characteristics of the elephant species (except for the considered frequency range) into account. The second baseline ("B2") clearly outperforms the approach of [7], both in detection rate and in false positive rate. The percentage of falsely classified frames is similar.…”

“…Figure 2 shows the large variation in duration of rumbles (from 0.5s to 2.5s). A more promising templatebased method for call detection has been recently introduced in [7]. The authors perform semi-supervised learning to select the sound snippet (template) that best discriminates between the positive and negative sound samples in a provided training set.…”

Real-time classification via sparse representation in acoustic sensor networks

“…The sampling frequency for this dataset is at 24kHz. The second dataset is from [21], which is available at http://www.cs.ucr.edu/~yhao/animalsoundfingerprint. html.…”