Next Article in Journal
An Electrochemical Amperometric Ethylene Sensor with Solid Polymer Electrolyte Based on Ionic Liquid
Next Article in Special Issue
Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing
Previous Article in Journal
A Robust Lane Detection Model Using Vertical Spatial Features and Contextual Driving Information
Previous Article in Special Issue
Multi-TALK: Multi-Microphone Cross-Tower Network for Jointly Suppressing Acoustic Echo and Background Noise
Open AccessArticle

Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures

1
Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia
2
Faculty of Computing and Informatics, Multimedia University, Cyberjaya 63100, Malaysia
3
IPTV Development, Unifi Content, Telekom Malaysia Berhad, Cyberjaya 63100, Malaysia
*
Author to whom correspondence should be addressed.
Academic Editor: Wookey Lee
Sensors 2021, 21(3), 710; https://doi.org/10.3390/s21030710
Received: 31 December 2020 / Revised: 16 January 2021 / Accepted: 19 January 2021 / Published: 21 January 2021
(This article belongs to the Special Issue VOICE Sensors with Deep Learning)
Given the excessive foul language identified in audio and video files and the detrimental consequences to an individual’s character and behaviour, content censorship is crucial to filter profanities from young viewers with higher exposure to uncensored content. Although manual detection and censorship were implemented, the methods proved tedious. Inevitably, misidentifications involving foul language owing to human weariness and the low performance in human visual systems concerning long screening time occurred. As such, this paper proposed an intelligent system for foul language censorship through a mechanized and strong detection method using advanced deep Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) through Long Short-Term Memory (LSTM) cells. Data on foul language were collected, annotated, augmented, and analysed for the development and evaluation of both CNN and RNN configurations. Hence, the results indicated the feasibility of the suggested systems by reporting a high volume of curse word identifications with only 2.53% to 5.92% of False Negative Rate (FNR). The proposed system outperformed state-of-the-art pre-trained neural networks on the novel foul language dataset and proved to reduce the computational cost with minimal trainable parameters. View Full-Text
Keywords: foul language; speech recognition; censorship; deep learning; convolutional neural networks; recurrent neural networks; long short-term memory foul language; speech recognition; censorship; deep learning; convolutional neural networks; recurrent neural networks; long short-term memory
Show Figures

Figure 1

MDPI and ACS Style

Ba Wazir, A.S.; Karim, H.A.; Abdullah, M.H.L.; AlDahoul, N.; Mansor, S.; Fauzi, M.F.A.; See, J.; Naim, A.S. Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures. Sensors 2021, 21, 710. https://doi.org/10.3390/s21030710

AMA Style

Ba Wazir AS, Karim HA, Abdullah MHL, AlDahoul N, Mansor S, Fauzi MFA, See J, Naim AS. Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures. Sensors. 2021; 21(3):710. https://doi.org/10.3390/s21030710

Chicago/Turabian Style

Ba Wazir, Abdulaziz S.; Karim, Hezerul A.; Abdullah, Mohd H.L.; AlDahoul, Nouar; Mansor, Sarina; Fauzi, Mohammad F.A.; See, John; Naim, Ahmad S. 2021. "Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures" Sensors 21, no. 3: 710. https://doi.org/10.3390/s21030710

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