# Marine Mammal Species Classification using Convolutional Neural Networks and a Novel Acoustic Representation

## TL;DR

This paper introduces a CNN-based system with a novel acoustic representation for classifying marine mammal vocalizations, effectively distinguishing species and noise sources in recordings for conservation efforts.

## Contribution

It presents a new acoustic signal representation and demonstrates transfer learning for marine mammal classification, improving generalization to additional species.

## Key findings

- Effective classification of whale vocalizations and noise sources.
- Novel acoustic representation enhances species discrimination.
- Transfer learning enables generalization to new species.

## Abstract

Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations of three species of whales, non-biological sources of noise, and a fifth class pertaining to ambient noise. In this way, the classifier is capable of detecting the presence and absence of whale vocalizations in an acoustic recording. Through transfer learning, we show that the classifier is capable of learning high-level representations and can generalize to additional species. We also propose a novel representation of acoustic signals that builds upon the commonly used spectrogram representation by way of interpolating and stacking multiple spectrograms produced using different Short-time Fourier Transform (STFT) parameters. The proposed representation is particularly effective for the task of marine mammal species classification where the acoustic events we are attempting to classify are sensitive to the parameters of the STFT.