scholarly journals Adaptive Noise Reduction for Sound Event Detection Using Subband-Weighted NMF

Sensors ◽  
2019 ◽  
Vol 19 (14) ◽  
pp. 3206 ◽  
Author(s):  
Qing Zhou ◽  
Zuren Feng ◽  
Emmanouil Benetos
Keyword(s):  
Noise Reduction ◽  
Event Detection ◽  
Reduction Method ◽  
Time Varying ◽  
Relative Importance ◽  
Noisy Signal ◽  
Sound Event ◽  
Sound Event Detection ◽  
Adaptive Noise ◽  
Non Negative Matrix Factorization

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). First, a scheme for noise dictionary learning from the input noisy signal is employed by the technique of robust NMF, which supports adaptation to noise variations. The estimated noise dictionary is used to develop a supervised source separation framework in combination with a pre-trained event dictionary. Second, to improve the separation quality, we extend the basic NMF model to a weighted form, with the aim of varying the relative importance of the different components when separating a target sound event from noise. With properly designed weights, the separation process is forced to rely more on those dominant event components, whereas the noise gets greatly suppressed. The proposed method is evaluated on a dataset of the rare sound event detection task of the DCASE 2017 challenge, and achieves comparable results to the top-ranking system based on convolutional recurrent neural networks (CRNNs). The proposed weighted NMF method shows an excellent noise reduction ability, and achieves an improvement of an F-score by 5%, compared to the unweighted approach.

scholarly journals Data-Dependent Feature Extraction Method Based on Non-Negative Matrix Factorization for Weakly Supervised Domestic Sound Event Detection

2021 ◽  
Vol 11 (3) ◽  
pp. 1040
Author(s):  
Seokjin Lee ◽  
Minhan Kim ◽  
Seunghyeon Shin ◽  
Sooyoung Park ◽  
Youngho Jeong
Keyword(s):  
Feature Extraction ◽  
Event Detection ◽  
Matrix Factorization ◽  
Extraction Method ◽  
Extraction Methods ◽  
Feature Extraction Method ◽  
Sound Event ◽  
Sound Event Detection ◽  
Weakly Supervised ◽  
Non Negative Matrix Factorization

In this paper, feature extraction methods are developed based on the non-negative matrix factorization (NMF) algorithm to be applied in weakly supervised sound event detection. Recently, the development of various features and systems have been attempted to tackle the problems of acoustic scene classification and sound event detection. However, most of these systems use data-independent spectral features, e.g., Mel-spectrogram, log-Mel-spectrum, and gammatone filterbank. Some data-dependent feature extraction methods, including the NMF-based methods, recently demonstrated the potential to tackle the problems mentioned above for long-term acoustic signals. In this paper, we further develop the recently proposed NMF-based feature extraction method to enable its application in weakly supervised sound event detection. To achieve this goal, we develop a strategy for training the frequency basis matrix using a heterogeneous database consisting of strongly- and weakly-labeled data. Moreover, we develop a non-iterative version of the NMF-based feature extraction method so that the proposed feature extraction method can be applied as a part of the model structure similar to the modern “on-the-fly” transform method for the Mel-spectrogram. To detect the sound events, the temporal basis is calculated using the NMF method and then used as a feature for the mean-teacher-model-based classifier. The results are improved for the event-wise post-processing method. To evaluate the proposed system, simulations of the weakly supervised sound event detection were conducted using the Detection and Classification of Acoustic Scenes and Events 2020 Task 4 database. The results reveal that the proposed system has F1-score performance comparable with the Mel-spectrogram and gammatonegram and exhibits 3–5% better performance than the log-Mel-spectrum and constant-Q transform.

A Survey of Polyphonic Sound Event Detection Based on Non-Negative Matrix Factorization

2016 ◽  
Author(s):  
Manh-Quan Bui ◽  
Viet-Hang Duong ◽  
Seksan Mathulaprangsan ◽  
Bach-Tung Pham ◽  
Wei-Jing Lee ◽  
...  
Keyword(s):  
Event Detection ◽  
Matrix Factorization ◽  
Sound Event ◽  
Sound Event Detection ◽  
Non Negative Matrix Factorization

An Effective Perturbation Based Semi-Supervised Learning Method for Sound Event Detection

2020 ◽  
Author(s):  
Xu Zheng ◽  
Yan Song ◽  
Jie Yan ◽  
Li-Rong Dai ◽  
Ian McLoughlin ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Event Detection ◽  
Learning Method ◽  
Sound Event ◽  
Sound Event Detection

Neural Network Distillation on IoT Platforms for Sound Event Detection

2019 ◽  
Author(s):  
Gianmarco Cerutti ◽  
Rahul Prasad ◽  
Alessio Brutti ◽  
Elisabetta Farella
Keyword(s):  
Neural Network ◽  
Event Detection ◽  
Sound Event ◽  
Iot Platforms ◽  
Sound Event Detection

scholarly journals Sound Event Detection in Underground Parking Garage Using Convolutional Neural Network

2020 ◽  
Vol 4 (3) ◽  
pp. 20 ◽  
Author(s):  
Giuseppe Ciaburro
Keyword(s):  
Event Detection ◽  
High Accuracy ◽  
Surveillance Systems ◽  
Urban Mobility ◽  
Parking Garage ◽  
Large Size ◽  
Car Crash ◽  
Sound Event ◽  
Parking Management ◽  
Sound Event Detection

Parking is a crucial element in urban mobility management. The availability of parking areas makes it easier to use a service, determining its success. Proper parking management allows economic operators located nearby to increase their business revenue. Underground parking areas during off-peak hours are uncrowded places, where user safety is guaranteed by company overseers. Due to the large size, ensuring adequate surveillance would require many operators to increase the costs of parking fees. To reduce costs, video surveillance systems are used, in which an operator monitors many areas. However, some activities are beyond the control of this technology. In this work, a procedure to identify sound events in an underground garage is developed. The aim of the work is to detect sounds identifying dangerous situations and to activate an automatic alert that draws the attention of surveillance in that area. To do this, the sounds of a parking sector were detected with the use of sound sensors. These sounds were analyzed by a sound detector based on convolutional neural networks. The procedure returned high accuracy in identifying a car crash in an underground parking area.

Sign in / Sign up

Export Citation Format

Share Document