by Zaharah Bukhsh, Aaqib Saeed @ 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Out-of-distribution (OOD) detection is concerned with identifying data points that do not belong to the same distribution as the model's training data. For the safe deployment of predictive models in a real-world environment, it is critical to avoid making confident predictions on OOD inputs as it can lead to potentially dangerous consequences. However, OOD detection largely remains an under-explored area in the audio (and speech) domain. This is despite the fact that audio is a central modality for many tasks, such as speaker diarization, automatic speech recognition, and sound event detection. To address this, we propose to leverage feature-space of the model with deep k-nearest neighbors to detect OOD samples. We show that this simple and flexible method effectively detects OOD inputs across a broad category of audio (and speech) datasets. Specifically, it improves the false positive rate (FPR@TPR95) by 17% and the AUROC score by 7% than other prior techniques.
We provide an example of running an OOD detection with Deep-kNN.
Install required packages:
The pretrained MobileNet (YAMNet) models are available from this link. Download and put them under models
directory.
python3 fe.py
Download precomputed features from here and put them under features
directory.
python3 run_ood.py
@article{bukhsh2022out,
title={On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors},
author={Bukhsh, Zaharah and Saeed, Aaqib},
journal={arXiv preprint arXiv:2210.15283},
year={2022}
}