Speech Detection System Research Articles

Detecting Hate Speech on Twitter Network using Ensemble Machine Learning

Twitter is habitually exploited now-a-days to propagate torrents of hate speeches, misogynistic, and misandry tweets that are written in slang. Machine learning methods have been explored in manifold studies to address the inherent challenges of hate speech detection in online spaces. Nevertheless, language has subtleties that can make it stiff for machines to adequately comprehend and disambiguate the semantics of words that are heavily dependent on the usage context. Deep learning methods have demonstrated promising results for automatic hate speech detection, but they require a significant volume of training data. Classical machine learning methods suffer from the innate problem of high variance that in turn affects the performance of hate speech detection systems. This study presents a voting ensemble machine learning method that harnesses the strengths of logistic regression, decision trees, and support vector machines for the automatic detection of hate speech in tweets. The method was evaluated against ten widely used machine learning methods on two standard tweet data sets using the famous performance evaluation metrics to achieve an improved average F1-score of 94.2%.

A New Hate Speech Detection System based on Textual and Psychological Features

Hate speech often spreads on social media and harms individuals and the community. Machine learning models have been proposed to detect hate speech in social media; however, several issues presently limit the performance of current approaches. One challenge is the issue of having diverse comprehensions of hate speech constructs which will lead to many speech categories and different interpretations. In addition, certain language-specific features, and short text issues, such as Twitter, exacerbate the problem. Moreover, current machine learning approaches lack universality due to small datasets and the adoption of a few features of hateful speech. This paper develops and builds new feature sets based on frequencies of textual tokens and psychological characteristics. Then, the study evaluates several machine learning methods over a large dataset. Results showed that the Random Forest and BERT methods are the most valuable for detecting hate speech content. Furthermore, the most dominant features that are helpful for hate speech detection methods combine psychological features and Term-Frequency Inverse Document-Frequency (TFIDF) features. Therefore, the proposed approach could identify hate speech on social media platforms like Twitter.

Political Hate Speech Detection and Lexicon Building: A Study in Taiwan

There is the minimal restriction to users’ speech in cyberspace. The Internet provides a space where people can freely present their speech, which puts a Utopian sense of freedom of speech into practice. However, the appearance of hate speech is a significant side effect of online freedom of speech. Some users use hate speech to attack others, making the attacked targets uncomfortable. The proliferation of hate speech poses severe challenges to cyber society. Users may hope that social media platforms and online communities promote anti-hate speech. However, hate speech detection is still a developing technology that requires system developers to create a method to detect unacceptable hate speech while maintaining the online freedom of speech environment. No excellence detection approach has yet been proposed, although some literature has focused on it. The current study proposes an approach to build a political hate speech lexicon and train artificial intelligence classifiers to detect hate speech. Our academic and practical contributions include the collection of a Chinese hate speech dataset, creating a Chinese hate speech lexicon, and developing both a deep learning-based and a lexicon-based approach to detect Chinese hate speech. Although we focus on Chinese hate speech detection, our proposed hate speech detection system and hate speech lexicon development approach can also be used for other languages.

Arabic Offensive and Hate Speech Detection Using a Cross-Corpora Multi-Task Learning Model

As social media platforms offer a medium for opinion expression, social phenomena such as hatred, offensive language, racism, and all forms of verbal violence have increased spectacularly. These behaviors do not affect specific countries, groups, or communities only, extending beyond these areas into people’s everyday lives. This study investigates offensive and hate speech on Arab social media to build an accurate offensive and hate speech detection system. More precisely, we develop a classification system for determining offensive and hate speech using a multi-task learning (MTL) model built on top of a pre-trained Arabic language model. We train the MTL model on the same task using cross-corpora representing a variation in the offensive and hate context to learn global and dataset-specific contextual representations. The developed MTL model showed a significant performance and outperformed existing models in the literature on three out of four datasets for Arabic offensive and hate speech detection tasks.

Overlapped speech detection using phase features.

Simultaneous speech of multiple speakers is known as overlapped speech, which causes problems for speech recognition and speaker diarization systems. The present work uses previously less utilized signal phase information in the task of overlapped speech detection. In this context, Instantaneous Frequency Cosine Coefficient (IFCC) and Modified Group Delay Cepstral Coefficient (MGDCC) features are explored. IFCC captures the time-varying phase characteristics, while MGDCC represents the frequency-varying information of the phase spectrum. A Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM)-based classifier is used for the classification. The present work uses synthetically generated overlapped speech from the GRID corpus. The proposed method is benchmarked against three baseline approaches that use magnitude spectrum features. It is observed that the combination of IFCC and MGDCC features with CNN-LSTM classifier provides better performance than the baselines. The combination of phase features with magnitude-based MFCC feature provides the best performance, indicating the importance of complementary information. The present study also investigates the effect of segment duration, genders, and number of simultaneous speakers on the overlapped speech detection system. Finally, the proposed method is also evaluated on real overlapped data from the AMI corpus.

Two-Sided LPC-Based Speckle Noise Removal for Laser Speech Detection Systems

Two-Sided LPC-Based Speckle Noise Removal for Laser Speech Detection Systems

Automatic Hate Speech Detection: A Literature Review

Hate speech has been an ongoing problem on the Internet for many years. Besides, social media, especially Facebook, and Twitter have given it a global stage where those hate speeches can spread far more rapidly. Every social media platform needs to implement an effective hate speech detection system to remove offensive content in real-time. There are various approaches to identify hate speech, such as Rule-Based, Machine Learning based, deep learning based and Hybrid approach. Since this is a review paper, we explained the valuable works of various authors who have invested their valuable time in studying to identifying hate speech using various approaches.

Automatic Hate Speech Detection: A Literature Review

Hate speech has been an ongoing problem on the Internet for many years. Besides, social media, especially Facebook, and Twitter have given it a global stage where those hate speeches can spread far more rapidly. Every social media platform needs to implement an effective hate speech detection system to remove offensive content in real-time. There are various approaches to identify hate speech, such as Rule-Based, Machine Learning based, deep learning based and Hybrid approach. Since this is a review paper, we explained the valuable works of various authors who have invested their valuable time in studying to identifying hate speech using various approaches.

Ambulatory Phonation Monitoring With Wireless Microphones Based on the Speech Energy Envelope: Algorithm Development and Validation.

BackgroundVoice disorders mainly result from chronic overuse or abuse, particularly in occupational voice users such as teachers. Previous studies proposed a contact microphone attached to the anterior neck for ambulatory voice monitoring; however, the inconvenience associated with taping and wiring, along with the lack of real-time processing, has limited its clinical application.ObjectiveThis study aims to (1) propose an automatic speech detection system using wireless microphones for real-time ambulatory voice monitoring, (2) examine the detection accuracy under controlled environment and noisy conditions, and (3) report the results of the phonation ratio in practical scenarios.MethodsWe designed an adaptive threshold function to detect the presence of speech based on the energy envelope. We invited 10 teachers to participate in this study and tested the performance of the proposed automatic speech detection system regarding detection accuracy and phonation ratio. Moreover, we investigated whether the unsupervised noise reduction algorithm (ie, log minimum mean square error) can overcome the influence of environmental noise in the proposed system.ResultsThe proposed system exhibited an average accuracy of speech detection of 89.9%, ranging from 81.0% (67,357/83,157 frames) to 95.0% (199,201/209,685 frames). Subsequent analyses revealed a phonation ratio between 44.0% (33,019/75,044 frames) and 78.0% (68,785/88,186 frames) during teaching sessions of 40-60 minutes; the durations of most of the phonation segments were less than 10 seconds. The presence of background noise reduced the accuracy of the automatic speech detection system, and an adjuvant noise reduction function could effectively improve the accuracy, especially under stable noise conditions.ConclusionsThis study demonstrated an average detection accuracy of 89.9% in the proposed automatic speech detection system with wireless microphones. The preliminary results for the phonation ratio were comparable to those of previous studies. Although the wireless microphones are susceptible to background noise, an additional noise reduction function can alleviate this limitation. These results indicate that the proposed system can be applied for ambulatory voice monitoring in occupational voice users.

Resources and benchmark corpora for hate speech detection: a systematic review

Hate Speech in social media is a complex phenomenon, whose detection has recently gained significant traction in the Natural Language Processing community, as attested by several recent review works. Annotated corpora and benchmarks are key resources, considering the vast number of supervised approaches that have been proposed. Lexica play an important role as well for the development of hate speech detection systems. In this review, we systematically analyze the resources made available by the community at large, including their development methodology, topical focus, language coverage, and other factors. The results of our analysis highlight a heterogeneous, growing landscape, marked by several issues and venues for improvement.

Hate speech detection and racial bias mitigation in social media based on BERT model.

Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been addressed more frequently, biases arising from trained classifiers have not yet been a matter of concern. In this paper, we first introduce a transfer learning approach for hate speech detection based on an existing pre-trained language model called BERT (Bidirectional Encoder Representations from Transformers) and evaluate the proposed model on two publicly available datasets that have been annotated for racism, sexism, hate or offensive content on Twitter. Next, we introduce a bias alleviation mechanism to mitigate the effect of bias in training set during the fine-tuning of our pre-trained BERT-based model for hate speech detection. Toward that end, we use an existing regularization method to reweight input samples, thereby decreasing the effects of high correlated training set’ s n-grams with class labels, and then fine-tune our pre-trained BERT-based model with the new re-weighted samples. To evaluate our bias alleviation mechanism, we employed a cross-domain approach in which we use the trained classifiers on the aforementioned datasets to predict the labels of two new datasets from Twitter, AAE-aligned and White-aligned groups, which indicate tweets written in African-American English (AAE) and Standard American English (SAE), respectively. The results show the existence of systematic racial bias in trained classifiers, as they tend to assign tweets written in AAE from AAE-aligned group to negative classes such as racism, sexism, hate, and offensive more often than tweets written in SAE from White-aligned group. However, the racial bias in our classifiers reduces significantly after our bias alleviation mechanism is incorporated. This work could institute the first step towards debiasing hate speech and abusive language detection systems.

Analytic phase features for dysarthric speech detection and intelligibility assessment

The objectives of the dysarthria assessment are to discriminate dysarthric speech from normal speech, to estimate the severity of dysarthria in terms of the dysarthric speech intelligibility, and to find the motor speech subsystem which causes defects in speech production. In this work, analytic phase features are investigated for the objective assessment of dysarthria. In this connection, the importance of analytic phase in speech intelligibility is studied by employing phase modification schemes. The current investigation on the analytic phase, proposed a novel approach to estimate the instantaneous frequency components from the speech signal, by using single frequency filtering technique. In this study, dysarthric speech detection and intelligibility assessment systems are developed by using UA-Speech database. The efficiency of the analytic phase features is compared with state-of-the-art spectral features. The proposed features outperformed the magnitude and group delay features and shown a classification accuracies of 95.61% and 64.47% for dysarthric speech detection and intelligibility assessment tasks, respectively. The fusion of the evidence obtained from the analytic phase and magnitude spectral features revealed the complementary nature of analytic phase features.

Computer-aided teaching mode of oral English intelligent learning based on speech recognition and network assistance

The purpose of this paper is to use English specific syllables and prosodic features in spoken speech data to carry out English spoken recognition, and to explore effective methods for the design and application of English speech detection and automatic recognition systems. The method proposed by this study is a combination of SVM_FF based classifier, SVM_IER based classifier and syllable classifier. Compared with the method based on the combination of other phonological characteristics such as phonological rate, intensity, formant and energy statistics and pronunciation rate, and the syllable-based classifier based on specific syllable training, a better recognition rate is obtained. In addition, this study conducts simulation experiments on the proposed English recognition and identification method based on specific syllables and prosodic features and analyzes the experimental results. The result found that the recognition performance of the English spoken recognition system constructed by this study is significantly better than the traditional model.

Spectro-temporal features for audio replay attack detection

Speaker verification can be viewed as a process of verifying the person using his/her utterance. The major challenge to implement automatic speaker verification in security applications is spoofing attacks. Speaker verification systems can be spoofed using pre-recorded speech, synthetic and voice conversion speech. Hence, there is a need to develop spoof detection system in order to make voice biometrics viable for security applications. This paper proposes to explore time-frequency representations obtained using gammatone filterbank and constant Q transform for detecting presentation attack for automatic speaker verification. The experiments are carried out for ASV spoof 2017 database and the results are compared with state-of-art replay speech detection systems based on cepstral features.

Quarantining online hate speech: technical and ethical perspectives

In this paper we explore quarantining as a more ethical method for delimiting the spread of Hate Speech via online social media platforms. Currently, companies like Facebook, Twitter, and Google generally respond reactively to such material: offensive messages that have already been posted are reviewed by human moderators if complaints from users are received. The offensive posts are only subsequently removed if the complaints are upheld; therefore, they still cause the recipients psychological harm. In addition, this approach has frequently been criticised for delimiting freedom of expression, since it requires the service providers to elaborate and implement censorship regimes. In the last few years, an emerging generation of automatic Hate Speech detection systems has started to offer new strategies for dealing with this particular kind of offensive online material. Anticipating the future efficacy of such systems, the present article advocates an approach to online Hate Speech detection that is analogous to the quarantining of malicious computer software. If a given post is automatically classified as being harmful in a reliable manner, then it can be temporarily quarantined, and the direct recipients can receive an alert, which protects them from the harmful content in the first instance. The quarantining framework is an example of more ethical online safety technology that can be extended to the handling of Hate Speech. Crucially, it provides flexible options for obtaining a more justifiable balance between freedom of expression and appropriate censorship.

94 GHz Millimeter Wave Conducted Speech Enhancement

The traditional microphone speech acquisition method has several limitations, such as short acquisition distance, non-directivity, weak ability to compensate for anti-acoustic noise, and poor sensitivity. As an alternative, our lab developed a new type of speech detection system using bio-radar. This novel speech detection method may effectively compensate for the shortcomings of the traditional microphone because of the special features of bio-radar. However, the detected radar speech is also corrupted by specific electromagnetic and ambient noises. Therefore, this study proposes a minimum mean-square error (MMSE) short-time spectral amplitude estimate algorithm to enhance radar captured speech. Because the proposed approach employs an optimal spectral amplitude estimator as well as a method to minimize the mean-square error of the log-spectra in enhancing noisy speech, this algorithm significantly reduces the colored residual noise. The enhanced radar speech was evaluated by both subjective and objective quality evaluation methods. The results demonstrate that the bio-radar can successfully detect speech signal and the proposed speech enhancement algorithm can improve radar captured speech quality.

Automatic hate speech detection in online contents using latent semantic analysis

Internet in general and social media in particular have greatly facilitated the communication, interaction and collaboration among people and different entities. As generally there is no censorship, these media sometimes are used to proliferate discourses that contain hateful messages targeting ethnic origin, religious or sexual groups, which potentially may degenerate to violent acts against individuals of such groups. Therefore, we explore the idea of building of automatic classifier that can be used for detection of hate speech in public Albanian language pages. A hate speech corpus for Albanian language is created, and then based on Support Vector Machine (SVM) approach, an automatic hate speech detection system is proposed. Such system can be used to detect and analyze hate speech in online contents over time and to enhance our knowledge on how they affect opinion creation in society.

Cochlear Filter and Instantaneous Frequency Based Features for Spoofed Speech Detection

Vulnerability of voice biometrics systems to spoofing attacks by synthetic speech (SS) and voice converted (VC) speech has arose the need of standalone spoofed speech detection (SSD) systems. This paper is an extension of our previously proposed features (used in relatively best performing SSD system) at the first ASVspoof 2015 challenge held at INTERSPEECH 2015. For the challenge, the authors proposed novel features based on cochlear filter cepstral coefficients (CFCC) and instantaneous frequency (IF), i.e., CFCCIF. The basic motivation behind this is that human ear processes speech in subbands. The envelope of each subband and its IF is important for perception of speech. In addition, the transient information also adds to the perceptual information that is captured. We observed that subband energy variations across CFCCIF when estimated by symmetric difference (CFCCIFS) gave better discriminative properties than CFCCIF. The features are extracted at frame level and the Gaussian mixture model based classification system was used. Experiments were conducted on ASVspoof 2015 challenge database with MFCC, CFCC, CFCCIF, and CFCCIFS features. On the evaluation dataset, after score-level fusion with MFCC, the CFCCIFS features gave an overall equal error rate (EER) of 1.45% as compared to 1.87% and 1.61% with CFCCIF and CFCC, respectively. In addition to detecting the known and unknown attacks, intensive experiments have been conducted to study the effectiveness of the features under the condition that either only SS or only VC speech is available for training. It was observed that when only VC speech is used in training, both VC, as well as SS, can be detected. However, when only SS is used in training, VC speech was not detected. In general, amongst vocoder-based spoofs, it was observed that VC speech is relatively difficult to detect than SS by the SSD system. However, vocoder-independent SS was toughest with highest EER (i.e., > 10%).

激光语音检测系统反正切补偿算法

激光语音检测系统反正切补偿算法

Synthetic speech detection using phase information

Taking advantage of the fact that most of the speech processing techniques neglect the phase information, we seek to detect phase perturbations in order to prevent synthetic impostors attacking Speaker Verification systems. Two Synthetic Speech Detection (SSD) systems that use spectral phase related information are reviewed and evaluated in this work: one based on the Modified Group Delay (MGD), and the other based on the Relative Phase Shift, (RPS). A classical module-based MFCC system is also used as baseline. Different training strategies are proposed and evaluated using both real spoofing samples and copy-synthesized signals from the natural ones, aiming to alleviate the issue of getting real data to train the systems. The recently published ASVSpoof2015 database is used for training and evaluation. Performance with completely unrelated data is also checked using synthetic speech from the Blizzard Challenge as evaluation material. The results prove that phase information can be successfully used for the SSD task even with unknown attacks.