Automated classification of bat echolocation call recordings with artificial intelligence

Acoustic recorders are commonly used to remotely monitor and collect data on bats (Order Chiroptera). These efforts result in many acoustic recordings that must be classified by a bat biologist with expertise in call classification in order to obtain useful information. The rarity of this expertise and time constraints have prompted efforts to automatically classify bat species in acoustic recordings using a variety of learning methods. There are several software programs available for this purpose, but they are imperfect and the United States Fish and Wildlife Service often recommends that a qualified acoustic analyst review bat call identifications even if using these software programs. We sought to build a model to classify bat species using modern computer vision techniques. We used images of bat echolocation calls (i.e., plots of the pulses) to train deep learning computer vision models that automatically classify bat calls to species. Our model classifies 10 species, five of which are protected under the Endangered Species Act. We evaluated our models using standard model validation procedures, but we also performed two out-of-distribution tests. For the out-of-distribution tests, an entire dataset was withheld from the procedure before splitting the data into training and validation sets. We found that our validation accuracy (93%) and out-of-distribution accuracy (90%) were higher than when we used Kaleidoscope Pro and BCID software (65% and 61% accuracy, respectively) to evaluate the same calls. Our results suggest that our approach is effective at classifying bat species from acoustic recordings, and our trained model will be incorporated into new bat call identification software: WEST-EchoVision.

Optimal features for auditory categorization

Humans and vocal animals use vocalizations (human speech or animal ‘calls’) to communicate with members of their species. A necessary function of auditory perception is to generalize across the high variability inherent in the production of these sounds and classify them into perceptually distinct categories (‘words’ or ‘call types’). Here, we demonstrate using an information-theoretic approach that production-invariant classification of calls can be achieved by detecting mid-level acoustic features. Starting from randomly chosen marmoset call features, we used a greedy search algorithm to determine the most informative and least redundant set of features necessary for call classification. Call classification at >95% accuracy could be accomplished using only 10 – 20 features per call type. Most importantly, predictions of the tuning properties of putative neurons selective for such features accurately matched some previously observed responses of superficial layer neurons in primary auditory cortex. Such a feature-based approach succeeded in categorizing calls of other species such as guinea pigs and macaque monkeys, and could also solve other complex classification tasks such as caller identification. Our results suggest that high-level neural representations of sounds are based on task-dependent features optimized for specific computational goals.

Investigation of domain adaptation for acoustic frog species classification

Acoustic frog species classification has received much attention for its importance in assessing biodiversity. However, most previous frog call classification models are trained and tested using the data collected from the same area, which greatly limits the model's generalization. In practice, frogs often have regional accents. When training and testing data are collected from different areas, there is an adverse impact on frog call classification performance. To tackle this problem, this paper investigates domain adaptation for classifying frog calls collected from different areas. To evaluate the performance of our proposed methods, two frog call datasets, which are collected from subtropical eastern Australia and tropical north-eastern Australia, are used. Experimental results demonstrate that domain adaptation can significantly improve the weighted F1-score from 72.8% to 85.5%.

Investigation of domain adaptation for acoustic frog species classification

Acoustic frog species classification has received much attention for its importance in assessing biodiversity. However, most previous frog call classification models are trained and tested using the data collected from the same area, which greatly limits the model's generalization. In practice, frogs often have regional accents. When training and testing data are collected from different areas, there is an adverse impact on frog call classification performance. To tackle this problem, this paper investigates domain adaptation for classifying frog calls collected from different areas. To evaluate the performance of our proposed methods, two frog call datasets, which are collected from subtropical eastern Australia and tropical north-eastern Australia, are used. Experimental results demonstrate that domain adaptation can significantly improve the weighted F1-score from 72.8% to 85.5%.