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

Wazir, Abdulaziz Saleh Ba; Karim, Hezerul Abdul; Abdullah, Muhammad; AlDahoul, Nouar; Mansor, Sarina; Fauzi, Mohammad Faizal Ahmad; See, John; Naim, Ahmad Syazwan

doi:10.3390/s21030710

Cited by 11 publications

(15 citation statements)

References 36 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e evaluation result analysis module is responsible for statistically analyzing the psychological evaluation results of users, discovering the psychological problems of users and grasping their psychological conditions at the first time, and providing help to users. is module can provide users with the analysis results of a single evaluation, comprehensive analysis results of multiple evaluations, function of filling in analysis opinions, and effectively and timely obtain user feedback information on the evaluation results [16].…”

Section: Evaluation Results Analysis Modulementioning

confidence: 99%

Design and Implementation of Online Intelligent Mental Health Testing Platform

Ren

Hou

Juz-he

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

In order to solve the problems of high misevaluation rate and low work efficiency in the process of mental health intelligent evaluation, a method of mental health intelligent evaluation system oriented to the decision tree algorithm is proposed. First, the current research status of mental health intelligent evaluation was analyzed and the framework of mental health intelligent evaluation system was constructed. Then, the mental health intelligent evaluation data were collected and the decision tree algorithm was used to analyze and classify the mental health intelligent evaluation data to obtain the mental health intelligent evaluation results. Finally, specific simulation experiments are used to analyze the feasibility and superiority of the mental health intelligent evaluation system. The experimental results show that the recall rate of each system increases with the increasing number of iterations, and the system has the highest recall rate. Also, it is stable after the number of iterations reaches 20, with good recall and adaptive scheduling performance. The recall rate of comparison system 1 and comparison system 2 fluctuates greatly, and the recall rate is lower than that of the system in this paper. It is proved that the method of the mental health intelligent evaluation system of the decision tree algorithm can effectively solve the problem and improve the accuracy of the mental health intelligent evaluation. The efficiency of mental health intelligent evaluation is improved, and the system stability is better, which can meet the actual requirements of current mental health intelligent evaluation.

show abstract

Section: Evaluation Results Analysis Modulementioning

confidence: 99%

Design and Implementation of Online Intelligent Mental Health Testing Platform

Ren

Hou

Juz-he

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Author details 1 Music Informatics Group, Georgia Institute of Technology, Atlanta, USA. 2 Netflix, Inc., Los Gatos, USA.…”

Section: Abbreviationsmentioning

confidence: 99%

“…SMAD aims to identify the temporal locations of speech, music, and their corresponding activity levels within a polyphonic mixture of audio signals. A reliable SMAD system can be used to extract relevant parts of audio signals in preparation for other speech or music focused tasks such as spoken language identification [1,2], speech recognition [3] and detection [4], speaker diarization, and singer identification [5]. For radio broadcasters and television services, by providing timing metadata about music and speech portion of the broadcasted content, SMAD can also help with a variety of tasks, such as data procurement for royalty payments and dialog loudness measurement.…”

Section: Introductionmentioning

confidence: 99%

A large TV dataset for speech and music activity detection

Hung

Orife

et al. 2022

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Automatic speech and music activity detection (SMAD) is an enabling task that can help segment, index, and pre-process audio content in radio broadcast and TV programs. However, due to copyright concerns and the cost of manual annotation, the limited availability of diverse and sizeable datasets hinders the progress of state-of-the-art (SOTA) data-driven approaches. We address this challenge by presenting a large-scale dataset containing Mel spectrogram, VGGish, and MFCCs features extracted from around 1600 h of professionally produced audio tracks and their corresponding noisy labels indicating the approximate location of speech and music segments. The labels are several sources such as subtitles and cuesheet. A test set curated by human annotators is also included as a subset for evaluation. To validate the generalizability of the proposed dataset, we conduct several experiments comparing various model architectures and their variants under different conditions. The results suggest that our proposed dataset is able to serve as a reliable training resource and leads to SOTA performances on various public datasets. To the best of our knowledge, this dataset is the first large-scale, open-sourced dataset that contains features extracted from professionally produced audio tracks and their corresponding frame-level speech and music annotations.

show abstract

“…Another work studied the categorization of isolated foul words versus isolated normal speech using a novel foul language dataset. Despite the acceptable performance on the tested dataset, the detection and localization performances within audio samples of the proposed methods (CNN and RNN) on other dataset consisting of conversational speech of continuous audios were not explored [66][67]. In brief, the feasibility of spoken profanity detection and localization within audio files has not been proven for real time audio filtering applications.…”

Section: Introductionmentioning

confidence: 98%

Deep Learning-Based Detection of Inappropriate Speech Content for Film Censorship

et al. 2022

Self Cite

View full text Add to dashboard Cite

Audible content has become an effective tool for shaping one's personality and character due to the ease of accessibility to a huge audible content that could be an independent audio files or an audio of online videos, movies, and television programs. There is a huge necessity to filter inappropriate audible content of the easily accessible videos and films that are likely to contain an inappropriate speech content. With this in view, all the broadcasting and online video/audio platform companies hire a lot of manpower to detect the foul voices prior to censorship. The process has a large cost in terms of manpower, time and financial resources. In addition to inaccurate detection of foul voices due to fatigue of manpower and weakness of human visual and hearing system in long time and monotonous tasks. As such, this paper proposes an intelligent deep learning-based system for film censorship through a fast and accurate detection and localization approach using advanced deep Convolutional Neural Networks (CNNs). The dataset of foul language containing isolated words samples and continuous speech were collected, annotated, processed, and analyzed for the development of automated detection of inappropriate speech content. The results indicated the feasibility of the suggested systems by reporting a high volume of inappropriate spoken terms detection. The proposed system outperformed state-of-the-art baseline algorithms on the novel foul language dataset evaluation metrics in terms of macro average AUC (93.85%), weighted average AUC (94.58%), and all other metrics such as F1-score. Additionally, proposed acoustic system outperformed ASR-based system for profanity detection based on the evaluation metrics including AUC, accuracy, precision, and F1-score. Additionally, proposed system was proven to be faster than human manual screening and detection of audible content for films' censorship.

show abstract

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

Cited by 11 publications

References 36 publications

Design and Implementation of Online Intelligent Mental Health Testing Platform

Design and Implementation of Online Intelligent Mental Health Testing Platform

A large TV dataset for speech and music activity detection

Deep Learning-Based Detection of Inappropriate Speech Content for Film Censorship

Contact Info

Product

Resources

About