In their paper titled "Detection of blue whale vocalisations using a temporal-domain convolutional neural network," authors Bryan Sagredo, Sonia Español-Jiménez, and Felipe Tobar present a framework for detecting blue whale vocalisations from acoustic submarine recordings. The proposed methodology consists of three stages: preprocessing, label-propagation, and convolutional neural network analysis. During the preprocessing stage, the audio recordings are conditioned through various techniques such as normalization, filtering, and denoising. This step aims to enhance the quality of the recordings and reduce background noise interference. The next stage involves a label-propagation mechanism that ensures the consistency of annotations for whale vocalisations. This mechanism helps maintain accurate labeling throughout the dataset by propagating labels based on similarity measures between different segments of vocalizations. Finally, a convolutional neural network is employed to analyze audio samples and detect blue whale vocalizations. The network is trained using 28 real-world submarine recordings while its performance is evaluated on six additional test recordings. The results demonstrate promising performance indicators including an accuracy of 85.4% and a recall rate of 93.5%. Furthermore, even in cases where the detector did not match ground-truth labels precisely, visual inspection confirms the ability of their approach to identify potential parts of whale calls that may have been unlabelled due to incomplete calls. Overall, this study presents an effective framework for detecting blue whale vocalizations from acoustic submarine recordings. The combination of preprocessing techniques, label propagation mechanisms and convolutional neural networks contributes to accurate detection with high performance indicators.
This is a study about finding blue whale sounds in recordings made underwater. The study has three steps: making the recordings better, making sure the labels for the whale sounds are correct, and using a special computer program to analyze the sounds. The program was trained with real recordings and tested on more recordings. It did a good job, with 85.4% accuracy and 93.5% recall rate. The program can even find parts of whale calls that are not complete yet. This study shows how to find blue whale sounds in underwater recordings."
Definitions
- Framework: A plan or structure that helps people do something.
- Vocalisations: Sounds made by animals.
- Acoustic: Related to sound or hearing.
- Submarine: A vehicle that can go underwater.
- Methodology: A way of doing something.
- Preprocessing: Making something better before using it.
- Label-propagation: Making sure labels or names are consistent or correct.
- Convolutional neural network: A type of computer program that can understand patterns in things like pictures or sounds.
- Analysis: Studying something carefully to understand it better.
- Trained: Taught or practiced so it knows how to do something well.
- Evaluated: Checked or tested to see how well it works.
- Performance indicators: Measurements that show how well something is doing its job.
- Accuracy: How correct something is compared to what is expected.
- Recall rate: How often something is remembered correctly compared to all the
Detecting Blue Whale Vocalizations Using a Temporal-Domain Convolutional Neural Network
In their paper titled "Detection of blue whale vocalisations using a temporal-domain convolutional neural network," authors Bryan Sagredo, Sonia Español-Jiménez, and Felipe Tobar present an effective framework for detecting blue whale vocalizations from acoustic submarine recordings. This study provides insight into the combination of preprocessing techniques, label propagation mechanisms and convolutional neural networks that contribute to accurate detection with high performance indicators.
Background
Blue whales are among the largest animals on Earth and play an important role in marine ecosystems. However, due to their elusive nature and vast migratory patterns, understanding their behavior is difficult. As such, acoustic recordings provide valuable information about blue whale populations as they can be used to identify individual whales through their unique calls. In order to accurately detect these calls from audio recordings collected by underwater microphones (hydrophones), researchers have proposed various approaches based on signal processing techniques such as Fourier transforms or wavelet decomposition.
Methodology
The proposed methodology consists of three stages: preprocessing, label-propagation, and convolutional neural network analysis. During the preprocessing stage, the audio recordings are conditioned through various techniques such as normalization, filtering, and denoising. This step aims to enhance the quality of the recordings and reduce background noise interference. The next stage involves a label-propagation mechanism that ensures the consistency of annotations for whale vocalisations. This mechanism helps maintain accurate labeling throughout the dataset by propagating labels based on similarity measures between different segments of vocalizations. Finally, a convolutional neural network is employed to analyze audio samples and detect blue whale vocalizations. The network is trained using 28 real-world submarine recordings while its performance is evaluated on six additional test recordings.
Results
The results demonstrate promising performance indicators including an accuracy of 85.4% and a recall rate of 93.5%. Furthermore, even in cases where the detector did not match ground-truth labels precisely, visual inspection confirms the ability of their approach to identify potential parts of whale calls that may have been unlabelled due to incomplete calls .
Conclusion
Overall this study presents an effective framework for detecting blue whale vocalizations from acoustic submarine recordings . The combination of preprocessing techniques , label propagation mechanisms ,and convolutional neural networks contributes to accurate detection with high performance indicators .
We present a framework for detecting blue whale vocalisations from acoustic submarine recordings. The proposed methodology comprises three stages: i) a preprocessing step where the audio recordings are conditioned through normalisation, filtering, and denoising; ii) a label-propagation mechanism to ensure the consistency of the annotations of the whale vocalisations, and iii) a convolutional neural network that receives audio samples. Based on 34 real-world submarine recordings (28 for training and 6 for testing) we obtained promising performance indicators including an Accuracy of 85.4\% and a Recall of 93.5\%. Furthermore, even for the cases where our detector did not match the ground-truth labels, a visual inspection validates the ability of our approach to detect possible parts of whale calls unlabelled as such due to not being complete calls.
