Limits...
Towards the Automatic Classification of Avian Flight Calls for Bioacoustic Monitoring

View Article: PubMed Central - PubMed

ABSTRACT

Automatic classification of animal vocalizations has great potential to enhance the monitoring of species movements and behaviors. This is particularly true for monitoring nocturnal bird migration, where automated classification of migrants’ flight calls could yield new biological insights and conservation applications for birds that vocalize during migration. In this paper we investigate the automatic classification of bird species from flight calls, and in particular the relationship between two different problem formulations commonly found in the literature: classifying a short clip containing one of a fixed set of known species (N-class problem) and the continuous monitoring problem, the latter of which is relevant to migration monitoring. We implemented a state-of-the-art audio classification model based on unsupervised feature learning and evaluated it on three novel datasets, one for studying the N-class problem including over 5000 flight calls from 43 different species, and two realistic datasets for studying the monitoring scenario comprising hundreds of thousands of audio clips that were compiled by means of remote acoustic sensors deployed in the field during two migration seasons. We show that the model achieves high accuracy when classifying a clip to one of N known species, even for a large number of species. In contrast, the model does not perform as well in the continuous monitoring case. Through a detailed error analysis (that included full expert review of false positives and negatives) we show the model is confounded by varying background noise conditions and previously unseen vocalizations. We also show that the model needs to be parameterized and benchmarked differently for the continuous monitoring scenario. Finally, we show that despite the reduced performance, given the right conditions the model can still characterize the migration pattern of a specific species. The paper concludes with directions for future research.

No MeSH data available.


Related in: MedlinePlus

Precision-recall (PR) curves for CLO-WTSP: training set (blue, obtained via 5-fold cross validation) and test set (red).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5120805&req=5

pone.0166866.g006: Precision-recall (PR) curves for CLO-WTSP: training set (blue, obtained via 5-fold cross validation) and test set (red).

Mentions: The ROC curve and AUC for the train and test sets are presented in Fig 5. We observed a drop in performance between the training and test sets, highlighting the challenge presented by this real-world scenario in which we must cope with mismatched conditions between the training and test sets (different location, different time of year). Further insight can be gained by examining the PR-curves for the train and test sets, presented in Fig 6. The difference in performance is more pronounced in the PR-curves, and allows us to make direct performance observations: the model could detect WTSP calls in the test set with relatively high precision (a low number of false positives) for recall values up to 0.4. For greater recall values (obtained by using more relaxed threshold values) the precision dropped markedly and the model became considerably less reliable.


Towards the Automatic Classification of Avian Flight Calls for Bioacoustic Monitoring
Precision-recall (PR) curves for CLO-WTSP: training set (blue, obtained via 5-fold cross validation) and test set (red).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5120805&req=5

pone.0166866.g006: Precision-recall (PR) curves for CLO-WTSP: training set (blue, obtained via 5-fold cross validation) and test set (red).
Mentions: The ROC curve and AUC for the train and test sets are presented in Fig 5. We observed a drop in performance between the training and test sets, highlighting the challenge presented by this real-world scenario in which we must cope with mismatched conditions between the training and test sets (different location, different time of year). Further insight can be gained by examining the PR-curves for the train and test sets, presented in Fig 6. The difference in performance is more pronounced in the PR-curves, and allows us to make direct performance observations: the model could detect WTSP calls in the test set with relatively high precision (a low number of false positives) for recall values up to 0.4. For greater recall values (obtained by using more relaxed threshold values) the precision dropped markedly and the model became considerably less reliable.

View Article: PubMed Central - PubMed

ABSTRACT

Automatic classification of animal vocalizations has great potential to enhance the monitoring of species movements and behaviors. This is particularly true for monitoring nocturnal bird migration, where automated classification of migrants’ flight calls could yield new biological insights and conservation applications for birds that vocalize during migration. In this paper we investigate the automatic classification of bird species from flight calls, and in particular the relationship between two different problem formulations commonly found in the literature: classifying a short clip containing one of a fixed set of known species (N-class problem) and the continuous monitoring problem, the latter of which is relevant to migration monitoring. We implemented a state-of-the-art audio classification model based on unsupervised feature learning and evaluated it on three novel datasets, one for studying the N-class problem including over 5000 flight calls from 43 different species, and two realistic datasets for studying the monitoring scenario comprising hundreds of thousands of audio clips that were compiled by means of remote acoustic sensors deployed in the field during two migration seasons. We show that the model achieves high accuracy when classifying a clip to one of N known species, even for a large number of species. In contrast, the model does not perform as well in the continuous monitoring case. Through a detailed error analysis (that included full expert review of false positives and negatives) we show the model is confounded by varying background noise conditions and previously unseen vocalizations. We also show that the model needs to be parameterized and benchmarked differently for the continuous monitoring scenario. Finally, we show that despite the reduced performance, given the right conditions the model can still characterize the migration pattern of a specific species. The paper concludes with directions for future research.

No MeSH data available.


Related in: MedlinePlus