North Atlantic Right Whales Up-call Detection Using Multimodel Deep Learning
This work addresses a domain-specific problem for marine biologists and conservationists by improving acoustic monitoring of an endangered species, though it is incremental as it builds on existing deep learning techniques.
The paper tackles the problem of detecting North Atlantic Right Whale up-calls by proposing a Multimodel Deep Learning approach that fuses CNNs and SAEs, achieving significantly better performance in detection rates and false alarm rates compared to conventional machine learning methods.
A new method for North Atlantic Right Whales (NARW) up-call detection using Multimodel Deep Learning (MMDL) is presented in this paper. In this approach, signals from passive acoustic sensors are first converted to spectrogram and scalogram images, which are time-frequency representations of the signals. These images are in turn used to train an MMDL detec-tor, consisting of Convolutional Neural Networks (CNNs) and Stacked Auto Encoders (SAEs). Our experimental studies revealed that CNNs work better with spectrograms and SAEs with sca-lograms. Therefore in our experimental design, the CNNs are trained by using spectrogram im-ages, and the SAEs are trained by using scalogram images. A fusion mechanism is used to fuse the results from individual neural networks. In this paper, the results obtained from the MMDL detector are compared with those obtained from conventional machine learning algorithms trained with handcraft features. It is shown that the performance of the MMDL detector is sig-nificantly better than those of the representative conventional machine learning methods in terms of up-call detection rate, non-up-call detection rate, and false alarm rate.