Abstract
Passive acoustic monitoring with hydrophones makes it possible to detect the presence of marine animals over large areas. For monitoring to be cost-effective, this process should be fully automated. We explore a new approach to detecting whale calls, using an end-to-end neural architecture and traditional speech features. We compare the results of the new approach with a convolutional neural network (CNN) applied to spectrograms, currently the standard approach to whale call detection. Experiments are conducted using the “Acoustic trends for the blue and fin whale library” from the Australian Antarctic Data Centre (AADC). We experiment with different types of speech features (mel frequency cepstral coefficients and filter banks) and different ways of framing the task. We demonstrate that a time delay neural network is a viable solution for whale call detection, with the additional benefit that spectrogram tuning – required to obtain high-quality spectrograms in challenging acoustic conditions – is no longer necessary. While the initial speech feature-based system (accuracy 96%) did not outperform the CNN (accuracy 98%) when trained on exactly the same dataset, it presents a viable approach to explore further.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Harvey, M.: Acoustic detection of humpback whales using a convolutional neural network (2018). https://ai.googleblog.com/2018/10/acoustic-detection-of-humpback-whales.html. Accessed 23 July 2021
Jiang, J.-J., Bu, L.-R., Duan, F.-J., et al.: Whistle detection and classification for whales based on convolutional neural networks. Appl. Acoust. 150, 169–178 (2019)
Jiang, J.-J., Bu, L.-R., Wang, X.-Q., et al.: Clicks classification of sperm whale and long-finned pilot whale based on continuous wavelet transform and artificial neural network. Appl. Acoust. 141, 26–34 (2018)
Shiu, Y., Palmer, K., Roch, M.A., et al.: Deep neural networks for automated detection of marine mammal species. Sci. Rep. 10(1), 1–12 (2020)
Cireşan, D., Meier, U., Masci, J., Schmidhuber, J.: A committee of neural networks for traffic sign classification. In: The 2011 International Joint Conference on Neural Networks, IEEE, pp. 1918–1921 (2011)
Bergler, C., Schröter, H., Cheng, R.X., et al.: Orca-spot: an automatic killer whale sound detection toolkit using deep learning. Sci. Rep. 9(1), 1–17 (2019)
Bermant, P.C., Bronstein, M.M., Wood, R.J., Gero, S., Gruber, D.F.: Deep machine learning techniques for the detection and classification of sperm whale bioacoustics. Sci. Rep. 9(1), 1–10 (2019)
Ravanelli, M., Parcollet, T., Plantinga, P., et al.: SpeechBrain: a generalpurpose speech toolkit(2021). arXiv: 2106.04624 [eess.AS]
Miller, B.S., Balcazar, N., Nieukirk, S., et al.: An open access dataset for developing automated detectors of antarctic baleen whale sounds and performance evaluation of two commonly used detectors. Sci. Rep. 11(1), 1–18 (2021)
Bahoura, M., Simard, Y.: Blue whale calls classification using shorttime fourier and wavelet packet transforms and artificial neural network. Digital Signal Process. 20(4), 1256–1263 (2010)
Lu, T., Han, B., Yu, F.: Detection and classification of marine mammal sounds using alexnet with transfer learning. Ecol. Inf. 62, 101277 (2021)
Yuea, H., Wanga, D., Zhanga, L., Wua, Y., Baoa, C., Wang, D.: Classification of whale calls based on transfer learning and convolutional neural network. In: 4th Underwater Acoustics Conference and Exhibition, pp. 537–544 (2017)
Usman, A.M., Versfeld, D.J.J.: Detection of baleen whale species using kernel dynamic mode decomposition-based feature extraction with a hidden Markov model. Ecol. Inf. 71, 101766 (2022)
Vaessen, N., Van Leeuwen, D.A.: Fine-tuning wav2vec2 for speaker recognition. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 7967–7971 (2022)
Singh, M., Pati, D.: Replay attack detection using excitation source and system features. In: Advances in Ubiquitous Computing, Elsevier, pp. 17–44 (2020)
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(3), 328–339 (1989). https://doi.org/10.1109/29.21701
Desplanques, B., Thienpondt, J., Demuynck, K.: Ecapa-tdnn: emphasized channel attention, propagation and aggregation in tdnn based speaker verification, arXiv preprint arXiv:2005.07143 (2020)
Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)
Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: Xvectors: robust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329–5333 (2018). https://doi.org/10.1109/ICASSP.2018.8461375
Pacific Northwest Seismic Network. “What is a spectrogram?” (2012). https://pnsn.org/spectrograms/what-is-a-spectrogram. Accessed 23 July 2021
Electrical4U. “Filter bank: What is it? (dct, polyphase, gabor, mel and fbmc).” (2021). https://www.electrical4u.com/filter-bank/. Accessed on 25 Aug 2022
Ogundile, O.O., Usman, A.M., Babalola, O.P., Versfeld, D.J.: Dynamic mode decomposition: a feature extraction technique based hidden Markov model for detection of mysticetes’ vocalisations. Ecol. Inf. 63,101306 (2021)
Imoscopi, S.: Machine learning for text-independent speaker verification (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Lim, Y.: State-of-the-art machine learning hyperparameter optimization with optuna (2021). Accessed on 08 Apr 2022
Park, D.S., Chan, W., Zhang, Y., et al.: Specaugment: a simple data augmentation method for automatic speech recognition, arXiv preprint arXiv:1904.08779 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization, arXiv preprint arXiv:1412.6980 (2014)
Ayuya, C.: Using random search to optimize hyperparameters (2022). https://www.section.io/engineering-education/random-search-hyperparameters/. Accessed 19 May 2022
Bouthillier, X., Tsirigotis, C., Corneau-Tremblay, F., et al.: Epistimio/orion: asynchronous Distributed Hyperparameter Optimization, version v0.2.4, May 2022. https://doi.org/10.5281/zenodo.3478592
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fourie, E., Davel, M.H., Versfeld, J. (2022). Neural Speech Processing for Whale Call Detection. In: Pillay, A., Jembere, E., Gerber, A. (eds) Artificial Intelligence Research. SACAIR 2022. Communications in Computer and Information Science, vol 1734. Springer, Cham. https://doi.org/10.1007/978-3-031-22321-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-22321-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22320-4
Online ISBN: 978-3-031-22321-1
eBook Packages: Computer ScienceComputer Science (R0)