You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection
arXiv:2109.00962 · doi:10.3390/app12073293
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. The relative improvement for F-measure of YOHO, compared to the state-of-the-art Convolutional Recurrent Neural Network, ranged from 1% to 6% across multiple datasets for audio segmentation and sound event detection. As the output of YOHO is more end-to-end and has fewer neurons to predict, the speed of inference is at least 6 times faster than segmentation-by-classification. In addition, as this approach predicts acoustic boundaries directly, the post-processing and smoothing is about 7 times faster.
19 pages, 4 figures, 8 tables. Added more experimental validation and background information. Published in Applied Sciences
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- A report on sound event detection with different binaural features
- Towards duration robust weakly supervised sound event detection
- Raw Waveform-based Audio Classification Using Sample-level CNN Architectures
- Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes