Next Article in Journal
Backlight Unit Excessive Dimming Based on Perceptual Image Analysis
Next Article in Special Issue
Shadow Estimation for Ultrasound Images Using Auto-Encoding Structures and Synthetic Shadows
Previous Article in Journal
Hybrid Spine Simulator Prototype for X-ray Free Pedicle Screws Fixation Training
Previous Article in Special Issue
Comparison of Dengue Predictive Models Developed Using Artificial Neural Network and Discriminant Analysis with Small Dataset
Open AccessArticle

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

1
School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Korea
2
School of Electronics Engineering, Kyungpook National University, Daegu 41566, Korea
3
Media Research Division, Electronics and Telecommunications Research Institute, Daejeon 34129, Korea
*
Author to whom correspondence should be addressed.
Academic Editor: Yoshinobu Kajikawa
Appl. Sci. 2021, 11(3), 1040; https://doi.org/10.3390/app11031040
Received: 18 December 2020 / Revised: 7 January 2021 / Accepted: 19 January 2021 / Published: 24 January 2021
(This article belongs to the Special Issue Machine Learning Methods with Noisy, Incomplete or Small Datasets)
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. View Full-Text
Keywords: feature extraction; sound event detection; non-negative matrix factorization feature extraction; sound event detection; non-negative matrix factorization
Show Figures

Figure 1

MDPI and ACS Style

Lee, S.; Kim, M.; Shin, S.; Park, S.; Jeong, Y. Data-Dependent Feature Extraction Method Based on Non-Negative Matrix Factorization for Weakly Supervised Domestic Sound Event Detection. Appl. Sci. 2021, 11, 1040. https://doi.org/10.3390/app11031040

AMA Style

Lee S, Kim M, Shin S, Park S, Jeong Y. Data-Dependent Feature Extraction Method Based on Non-Negative Matrix Factorization for Weakly Supervised Domestic Sound Event Detection. Applied Sciences. 2021; 11(3):1040. https://doi.org/10.3390/app11031040

Chicago/Turabian Style

Lee, Seokjin; Kim, Minhan; Shin, Seunghyeon; Park, Sooyoung; Jeong, Youngho. 2021. "Data-Dependent Feature Extraction Method Based on Non-Negative Matrix Factorization for Weakly Supervised Domestic Sound Event Detection" Appl. Sci. 11, no. 3: 1040. https://doi.org/10.3390/app11031040

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop