Improved spectral dynamic features extracted from audio data for classification of marine vessels

Abstract

Underwater sound classification presents a unique challenge due to the complex propagation characteristics of sound in water, including absorption, scattering, and refraction. These complexities can distort and alter spectral features, hindering the effectiveness of traditional feature extraction methods for vessel classification. To address this challenge, this study proposes a novel feature extraction method that combines Mel-frequency cepstral coefficients (MFCCs) with a spectral dynamic feature (SDF) vector. MFCCs capture the spectral content of the audio signal, whereas SDF provides information on the temporal dynamics of spectral features. This combined approach aims to achieve a more comprehensive representation of underwater vessel sounds, potentially leading to improved classification accuracy. Validation with real-world underwater audio recordings demonstrated the effectiveness of the proposed method. Results indicated an improvement of up to 94.68% in classification accuracy when combining SDF with several classical extractors evaluated. This finding highlights the potential of SDF in overcoming the challenges associated with underwater sound classification.

Keywords

Underwater sound classification / Feature extraction / Cepstral domain / Vessel classification / Mel filter bank

References

[1] Alcaraz Meseguer N (2009) Speech analysis for automatic speech recognition. Master’s thesis, Department of Electronics and Telecommunications

[2] Bianco MJ, Gerstoft P, Traer J, Ozanich E, Roch MA, Gannot S, Deledalle CA. Machine learning in acoustics: theory and applications. J Acoust Soc Am, 2019, 146(5): 3590-3628,

[3] Chen Y, Xu X (2017) The research of underwater target recognition method based on deep learning. In: 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xiamen, pp 1–5. https://doi.org/10.1109/ICSPCC.2017.8242464

[4] Das A, Kumar A, Bahl R. Marine vessel classification based on passive sonar data: the cepstrum-based approach. IET Radar, Sonar Navig, 2013, 7(1): 87-93,

[5] Dixit A, Vidwans A, Sharma P (2016) Improved MFCC and LPC algorithm for Bundelkhandi isolated digit speech recognition. In: 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), Chennai, pp 3755–3759

[6] Jordan MI, Mitchell TM. Machine learning: Trends, perspectives, and prospects. Science, 2015, 349(6245): 255-260,

[7] Karbasi M, Ahadi SM, Bahmanian M. Environmental sound classification using spectral dynamic features. 2011 8th International Conference on Information, 2011 Singapore Communications & Signal Processing 1-5

[8] Li XX, Yang S, Yu M (2008) Feature extraction from underwater signals using wavelet packet transform. In: 2008 International Conference on Neural Networks and Signal Processing, Nanjing, pp 400–405. https://doi.org/10.1109/ICNNSP.2008.4590381

[9] Lian Z, Xu K, Wan J, Li G (2017) Underwater acoustic target classification based on modified GFCC features. In: 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, pp 258–262. https://doi.org/10.1109/IAEAC.2017.8054017

[10] Liu J, He Y, Liu Z, Xiong Y (2014) Underwater target recognition based on line spectrum and support vector machine. In: Proceedings of the 2014 International Conference on Mechatronics, Control and Electronic Engineering, Shenyang, pp 79–84. https://doi.org/10.2991/mce-14.2014.17

[11] Majeed SA, Husain H, Samad SA, Idbeaa T. Mel frequency cepstral coefficients (MFCC) feature extraction enhancement in the application of speech recognition: a comparison study. J of Theor Appl Inf Technol, 2015, 79(1): 38-56

[12] McKenna MF, Ross D, Wiggins SM, Hildebrand JA. Underwater radiated noise from modern commercial ships. J Acoust Soc Am, 2012, 131(1): 92-103,

[13] Rabiner LR, Juang BH. . Fundamentals of speech recognition, 1999 Beijing Tsinghua University Press

[14] Rao KS, Manjunath KE. . Speech recognition using articulatory and excitation source features, 2017 Cham Springer,

[15] Sabara R, Soares C, Zabel F, Oliveira J, Jesus S (2020) Automatic acoustic target detection and classification off the coast of portugal. In: Global Oceans 2020: Singapore–U.S. Gulf Coast, Biloxi, pp 1–9. https://doi.org/10.1109/IEEECONF38699.2020.9389067

[16] Santos-Domínguez D, Torres-Guijarro S, Cardenal-López A, Pena-Gimenez A. ShipsEar: An underwater vessel noise database. Appl Acoust, 2016, 113: 64-69,

[17] Saravanan R, Sujatha P (2018) A state of art techniques on machine learning algorithms: a perspective of supervised learning approaches in data classification. In: 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, pp 945–949

[18] Sharma G, Umapathy K, Krishnan S. Trends in audio signal feature extraction methods. Appl Acoust, 2020, 158: 107020,

[19] Tong Y, Zhang X, Ge Y (2020) Classification and recognition of underwater target based on MFCC feature extraction. In: 2020 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Macau, pp 1–4. https://doi.org/10.1109/ICSPCC50002.2020.9259457

[20] Trang H, Tran L, Nam H (2015) Proposed combination of PCA and MFCC feature extraction in speech recognition system. In: 2014 International Conference on Advanced Technologies for Communications (ATC 2014), Hanoi, pp 697–702. https://doi.org/10.1109/ATC.2014.7043477

[21] Winursito A, Hidayat R, Bejo A (2018) Improvement of MFCC feature extraction accuracy using PCA in indonesian speech recognition. In: 2018 International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, pp 379–383

[22] Yao Q, Wang Y, Yang Y. Underwater acoustic target recognition based on data augmentation and residual CNN. Electronics, 2023, 12(5): 1206,

[23] Zhang Q, Da L, Zhang Y, Hu Y. Integrated neural networks based on feature fusion for underwater target recognition. Appl Acoust, 2021, 182: 108261,

[24] Zhang Y, Jiao L, Hu S (1998) An efficient method of target classification. In: ICSP ’98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344), Beijing, pp 1181–1184. https://doi.org/10.1109/ICOSP.1998.770828