A Wavelet Based Disaggregation Approach for Unusual Audio Detection

Vrindavanam, Jayavrinda; Srinath, Raghunandan

doi:10.1109/incet49848.2020.9154128

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this model only provides information about the presence of the rare event in an audio clip, without its time of occurrence. The model in [ 43 ] proposes the use of an SVM to cluster the features extracted from the audio by WSN for detecting any change in the ambient routine of elderly people. However, neither results are reported in their paper, nor any comparison is made with other models.…”

Section: Introductionmentioning

confidence: 99%

“…Although the model of [ 43 ] is designed for SED and is very much similar to our proposed system in using the WSN for feature extraction and later SVM for their classification, the main difference lies in the fact that their model uses no denoising mechanism before extracting features by WSN. Also, as they have not reported their results and have trained their model on their self-recorded dataset, it is not possible to compare our proposed algorithm with [ 43 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DEW: A wavelet approach of rare sound event detection

Gul,

Khan,

Ur-Rehman

2024

PLoS ONE

View full text Add to dashboard Cite

This paper presents a novel sound event detection (SED) system for rare events occurring in an open environment. Wavelet multiresolution analysis (MRA) is used to decompose the input audio clip of 30 seconds into five levels. Wavelet denoising is then applied on the third and fifth levels of MRA to filter out the background. Significant transitions, which may represent the onset of a rare event, are then estimated in these two levels by combining the peak-finding algorithm with the K-medoids clustering algorithm. The small portions of one-second duration, called ‘chunks’ are cropped from the input audio signal corresponding to the estimated locations of the significant transitions. Features from these chunks are extracted by the wavelet scattering network (WSN) and are given as input to a support vector machine (SVM) classifier, which classifies them. The proposed SED framework produces an error rate comparable to the SED systems based on convolutional neural network (CNN) architecture. Also, the proposed algorithm is computationally efficient and lightweight as compared to deep learning models, as it has no learnable parameter. It requires only a single epoch of training, which is 5, 10, 200, and 600 times lesser than the models based on CNNs and deep neural networks (DNNs), CNN with long short-term memory (LSTM) network, convolutional recurrent neural network (CRNN), and CNN respectively. The proposed model neither requires concatenation with previous frames for anomaly detection nor any additional training data creation needed for other comparative deep learning models. It needs to check almost 360 times fewer chunks for the presence of rare events than the other baseline systems used for comparison in this paper. All these characteristics make the proposed system suitable for real-time applications on resource-limited devices.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%