A No-Reference Model for Detecting Audio Artifacts Using Pretrained Audio Neural Networks

David Higham, Ayush Bagla, Veneta Haralampieva; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2022, pp. 9-13

Abstract


This work presents a No-Reference model to detect audio artifacts in video. The model, based upon a Pretrained Audio Neural Network, classifies a 1 second audio segment as either: No Defect, Audio Hum, Audio Hiss, Audio Distortion or Audio Clicks. The model achieves a balanced accuracy of 0.986 on our proprietary simulated dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Higham_2022_WACV, author = {Higham, David and Bagla, Ayush and Haralampieva, Veneta}, title = {A No-Reference Model for Detecting Audio Artifacts Using Pretrained Audio Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {January}, year = {2022}, pages = {9-13} }