Logo image
Back
Underwater Acoustic Signal Classification using Hierarchical Audio Transformer with Noisy Input
Conference paper

Underwater Acoustic Signal Classification using Hierarchical Audio Transformer with Noisy Input

Quoc Thinh Vo and David Kyonghun Han
2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)
18 Sep 2023
DOI: https://doi.org/10.1109/MLSP55844.2023.10285893

Abstract

audio transformer Frequency-domain analysis mel-spectrogram Oceans Pattern classification Robustness time frequency domain Transformers underwater acoustic classification underwater Underwater acoustic signal classification Machine Learning Signal Processing
Classifying different acoustic sources has been a challenge in underwater environment due to the difficulties of acquiring data in ocean environment and also due to the variety of background noise it poses. Self-attention mechanism has been shown to be effective in various machine learning tasks in challenging environments with sparse dataset. An audio transformer, designed for air acoustics, was modified and adapted for underwater sound classification task. We demonstrate the effectiveness of our method by applying to the shipsEar dataset [1], and show that the proposed method outperforms some of the latest classification methods. We also show its robustness in high noise environments.

Metrics

13 Record Views

Details

Logo image