Frequency Tracking Features for Data-Efficient Deep Siren Identification
Preprint
Abstract
The identification of siren sounds in urban soundscapes is a crucial safety aspect for smart vehicles and has been widely addressed by means of neural networks that ensure robustness to both the diversity of siren signals and the strong and unstructured background noise characterizing traffic. Convolutional neural networks analyzing spectrogram features of incoming signals achieve state-of-the-art performance when enough training data capturing the diversity of the target acoustic scenes is available. In practice, data is usually limited and algorithms should be robust to adapt to unseen acoustic conditions without requiring extensive datasets for re-training. In this work, given the harmonic nature of siren signals, characterized by a periodically evolving fundamental frequency, we propose a low-complexity feature extraction method based on frequency tracking using a single-parameter adaptive notch filter. The features are then used to design a small-scale convolutional network suitable for training with limited data. The evaluation results indicate that the proposed model consistently outperforms the traditional spectrogram-based model when limited training data is available, achieves better cross-domain generalization and has a smaller size.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Synthetic data generation techniques for training deep acoustic siren identification networksFrontiers in Signal Processing, 2024
- Large-scale audio dataset for emergency vehicle sirens and road noisesScientific Data, 2022
- A siren identification system using deep learning to aid hearing-impaired peopleEngineering Applications of Artificial Intelligence, 2022
- Listening for Sirens: Locating and Classifying Acoustic Alarms in City ScenesIEEE Transactions on Intelligent Transportation Systems, 2022
- How Well Can Driverless Vehicles Hear? An Introduction to Auditory Perception for Autonomous and Smart VehiclesIEEE Intelligent Transportation Systems Magazine, 2021
- Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural NetworksIEEE Access, 2020
- Intelligent Traffic Monitoring Systems for Vehicle Classification: A SurveyIEEE Access, 2020
- Fifty Years of Acoustic Feedback Control: State of the Art and Future ChallengesProceedings of the IEEE, 2010
- Adaptive notch filtering for the retrieval of sinusoids in noiseIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960