Search

Continuous recording of environmental sounds could allow long-term monitoring of vocal wildlife, and scaling of ecological studies to large temporal and spatial scales. However, such opportunities are currently limited by constraints in the analysis of large acoustic data sets. Computational methods and automation of call detection require specialist expertise and are time consuming to develop, therefore most biological researchers continue to use manual listening and inspection of spectrograms to analyze their sound recordings. False-color spectrograms were recently developed as a tool to allow visualization of long-duration sound recordings, intending to aid ecologists in navigating their audio data and detecting species of interest. This paper explores the efficacy of using this visualization method to identify multiple frog species in a large set of continuous sound recordings and gather data on the chorusing activity of the frog community. We found that, after a phase of training of the observer, frog choruses could be visually identified to species with high accuracy. We present a method to analyze such data, including a simple R routine to interactively select short segments on the false-color spectrogram for rapid manual checking of visually identified sounds. We propose these methods could fruitfully be applied to large acoustic data sets to analyze calling patterns in other chorusing species.

This paper presents a successful application of deep learning for object recognition based on acoustic data. The shortcomings of previously employed approaches where handcrafted features describing the acoustic data are being used, include limiting the capability of the found representation to be widely applicable and facing the risk of capturing only insignificant characteristics for a task. In contrast, there is no need to define the feature representation format when using multilayer/deep learning architecture methods: features can be learned from raw sensor data without defining discriminative characteristics a-priori. In this paper, stacked denoising autoencoders are applied to train a deep learning model. Knocking each object in our test set 120 times with a marker pen to obtain the auditory data, thirty different objects were successfully classified in our experiment and each object was knocked 120 times by a marker pen to obtain the auditory data. By employing the proposed deep learning framework, a high accuracy of 91.50% was achieved. A traditional method using handcrafted features with a shallow classifier was taken as a benchmark and the attained recognition rate was only 58.22%. Interestingly, a recognition rate of 82.00% was achieved when using a shallow classifier with raw acoustic data as input. In addition, we could show that the time taken to classify one object using deep learning was far less (by a factor of more than 6) than utilizing the traditional method. It was also explored how different model parameters in our deep architecture affect the recognition performance. [ABSTRACT FROM AUTHOR]

Acoustic sensors can be used to estimate species richness for vocal species such as birds. They can continuously and passively record large volumes of data over extended periods. These data must subsequently be analyzed to detect the presence of vocal species. Automated analysis of acoustic data for large numbers of species is complex and can be subject to high levels of false positive and false negative results. Manual analysis by experienced surveyors can produce accurate results; however the time and effort required to process even small volumes of data can make manual analysis prohibitive. This study examined the use of sampling methods to reduce the cost of analyzing large volumes of acoustic sensor data, while retaining high levels of species detection accuracy. Utilizing five days of manually analyzed acoustic sensor data from four sites, we examined a range of sampling frequencies and methods including random, stratified, and biologically informed. We found that randomly selecting 120 one-minute samples from the three hours immediately following dawn over five days of recordings, detected the highest number of species. On average, this method detected 62% of total species from 120 one-minute samples, compared to 34% of total species detected from traditional area search methods. Our results demonstrate that targeted sampling methods can provide an effective means for analyzing large volumes of acoustic sensor data efficiently and accurately. Development of automated and semi-automated techniques is required to assist in analyzing large volumes of acoustic sensor data. [ABSTRACT FROM AUTHOR]

Echo-integration measurements have been traditionally made from dedicated fisheries survey vessels, but extensive measurements from moorings, autonomous vehicles, and fishing vessels are increasingly available. Processing these data by traditional means developed for well-staffed fisheries surveys can be prohibitively time-consuming, which has limited their use. Automated processing methods exist to efficiently handle these large datasets; however, as compared to post-processing by trained analysts, these methods require substantial expertise and methodological development, and they often produce less certain results. Here, we evaluate the use of subsampling, which takes advantage of the spatial correlation common in many fish populations, to improve the efficiency of traditional processing methods while retaining a high level of precision. We subsampled data from an eastern Bering Sea walleye pollock (Gadus chalcogrammus) acoustic-trawl survey and compared estimates of pollock backscatter from subsamples to those from the full survey. Over a survey-wide scale, processing < 5% of the data resulted in estimates within 5% of those from processing the full survey. This suggests that in some applications there may be diminishing returns associated with exhaustively processing large spatially correlated datasets. We present an example that applies this simple approach by subsampling archived echosounder data from chartered fishing vessels to prioritize the areas surveyed in future surveys, which would not have been feasible without subsampling. When averaged values over large scales (e.g. over a survey domain) are required, precise echo integration estimates can be obtained with modest effort by processing relatively small subsamples of a dataset. [ABSTRACT FROM AUTHOR]