%0 Generic %1 venkatesh2021yololike %A Venkatesh, Satvik %A Moffat, David %A Miranda, Eduardo Reck %D 2021 %K audio segmentation singleshot %T You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection %U http://arxiv.org/abs/2109.00962 %X Audio segmentation and sound event detection are crucial topics in machine listening that aim to detect acoustic classes and their respective boundaries. It is useful for audio-content analysis, speech recognition, audio-indexing, and music information retrieval. In recent years, most research articles adopt segmentation-by-classification. This technique divides audio into small frames and individually performs classification on these frames. In this paper, we present a novel approach called You Only Hear Once (YOHO), which is inspired by the YOLO algorithm popularly adopted in Computer Vision. We convert the detection of acoustic boundaries into a regression problem instead of frame-based classification. This is done by having separate output neurons to detect the presence of an audio class and predict its start and end points. YOHO obtained a higher F-measure and lower error rate than the state-of-the-art Convolutional Recurrent Neural Network on multiple datasets. As YOHO is purely a convolutional neural network and has no recurrent layers, it is faster during inference. In addition, as this approach is more end-to-end and predicts acoustic boundaries directly, it is significantly quicker during post-processing and smoothing.

@misc{venkatesh2021yololike, abstract = {Audio segmentation and sound event detection are crucial topics in machine listening that aim to detect acoustic classes and their respective boundaries. It is useful for audio-content analysis, speech recognition, audio-indexing, and music information retrieval. In recent years, most research articles adopt segmentation-by-classification. This technique divides audio into small frames and individually performs classification on these frames. In this paper, we present a novel approach called You Only Hear Once (YOHO), which is inspired by the YOLO algorithm popularly adopted in Computer Vision. We convert the detection of acoustic boundaries into a regression problem instead of frame-based classification. This is done by having separate output neurons to detect the presence of an audio class and predict its start and end points. YOHO obtained a higher F-measure and lower error rate than the state-of-the-art Convolutional Recurrent Neural Network on multiple datasets. As YOHO is purely a convolutional neural network and has no recurrent layers, it is faster during inference. In addition, as this approach is more end-to-end and predicts acoustic boundaries directly, it is significantly quicker during post-processing and smoothing.}, added-at = {2022-03-08T09:49:54.000+0100}, author = {Venkatesh, Satvik and Moffat, David and Miranda, Eduardo Reck}, biburl = {https://www.bibsonomy.org/bibtex/29695a761267d44a7f7be1c13bfcac84d/annakrause}, description = {[2109.00962] You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection}, interhash = {e0dd5369a04a8b31e886d111f68708e3}, intrahash = {9695a761267d44a7f7be1c13bfcac84d}, keywords = {audio segmentation singleshot}, note = {cite arxiv:2109.00962Comment: 20 pages, 4 figures, 6 tables. Added more experimental validation}, timestamp = {2022-03-08T09:49:54.000+0100}, title = {You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection}, url = {http://arxiv.org/abs/2109.00962}, year = 2021 }