Hate speech has spread more rapidly through the daily use of technology and, most notably, by sharing your opinions or feelings on social media in a negative aspect. Although numerous works have been carried out in detecting hate speeches in English, German, and other languages, very few works have been carried out in the context of the Bengali language. In contrast, millions of people communicate on social media in Bengali. The few existing works that have been carried out need (...) improvements in both accuracy and interpretability. This article proposed encoder–decoder-based machine learning model, a popular tool in NLP, to classify user’s Bengali comments from Facebook pages. A dataset of 7,425 Bengali comments, consisting of seven distinct categories of hate speeches, was used to train and evaluate our model. For extracting and encoding local features from the comments, 1D convolutional layers were used. Finally, the attention mechanism, LSTM, and GRU-based decoders have been used for predicting hate speech categories. Among the three encoder–decoder algorithms, attention-based decoder obtained the best accuracy (77%). (shrink)

This investigation examined age-related differences in auditory-visual integration as reflected on perceptual judgments of temporally misaligned AV English sentences spoken by native English and native Spanish talkers. In the detection task, it was expected that slowed auditory temporal processing of older participants, relative to younger participants, would be manifest as a shift in the range over which participants would judge asynchronous stimuli as synchronous. The older participants were also expected to exhibit greater declines in speech recognition for asynchronous (...) AV stimuli than younger participants. Talker accent was hypothesized to influence listener performance, with older listeners exhibiting a greater narrowing of the AV simultaneity window and much poorer recognition of asynchronous AV foreign-accented speech compared to younger listeners. Participant groups included younger and older participants with normal hearing and older participants with hearing loss. Stimuli were video recordings of sentences produced by native English and native Spanish talkers. The video recordings were altered in 50 ms steps by delaying either the audio or video onset. Participants performed a detection task in which they judged whether the sentences were synchronous or asynchronous, and performed a recognition task for multiple synchronous and asynchronous conditions. Both the detection and recognition tasks were conducted at the individualized signal-to-noise ratio corresponding to approximately 70% correct speech recognition performance for synchronous AV sentences. Older listeners with and without hearing loss generally showed wider AV simultaneity windows than younger listeners, possibly reflecting slowed auditory temporal processing in auditory lead conditions and reduced sensitivity to asynchrony in auditory lag conditions. However, older and younger listeners were affected similarly by misalignment of auditory and visual signal onsets on the speech recognition task. This suggests that older listeners are negatively impacted by temporal misalignments for speech recognition, even when they do not notice that the stimuli are asynchronous. Overall, the findings show that when listener performance is equated for simultaneous AV speech signals, age effects are apparent in detection judgments but not in recognition of asynchronous speech. (shrink)

. Epochs present in the voiced speech are defined as time instants of significant excitation of the vocal tract system during the production of speech. Nonstationary nature of excitation source and vocal tract system makes accurate identification of epochs a difficult task. Most of the existing methods for epoch detection require prior knowledge of voiced regions and a rough estimation of pitch frequency. In this paper, we propose a novel method that relies on time-order representation based on (...) short-time Fourier–Bessel series expansion which can be employed on entire speech signal to detect epochs without any prior information. The proposed method automatically detects voiced regions in the speech signal by computing the marginal energy density with respect to time in the low frequency range from the energy distribution in the time-frequency plane. An estimate of pitch frequency for each detected voiced region is then obtained by computing the marginal energy density with respect to frequency in the LFR from the energy distribution in the time-frequency plane. Epochs are located for each detected voiced region as peaks in the derivative of the low pass filtered signal corresponding to falling edges of peak negative cycles in the LPF signal synthesized from TOR coefficients corresponding to LFR. Experimental results obtained by the proposed method on speech signals taken from the CMU-Arctic database are found to be promising. The proposed method detects epochs with high accuracy and reliability. (shrink)

Inner speech is commonly understood as the conscious experience of a voice within the mind. One recurrent theme in the scientific literature is that the phenomenon involves a representation of overt speech, for example, a representation of phonetic properties that result from a copy of speech instructions that were ultimately suppressed. I propose a larger picture that involves some embodied objects and their misperception. I call it “the Body Error Theory,” or BET for short. BET is a (...) form of illusionism, but the particular version I favor is a cross-modal illusion. Newly described here, my hypothesis is that the experience of inner speech arises from a mix of interoception and audition. Specifically, there is the detection of slight but well-confirmed activities in the speech musculature that occur during inner speech, which helps to transform representations of normal but quiet nonverbal sounds that inevitably occur during inner speech, from breathing to background noise, into a mistaken perception of inner speech. Simply put, activities in the speech musculature mix with sounds to create the appearance of speech sounds, which thus explains the “voice within the mind.” I also show how BET’s cross-modal system fits with standard information processing accounts for speech monitoring and how it accommodates the central insights of leading theories of inner speech. In addition, I show how BET is supported by data from experience-sampling surveys and how it can be empirically tested against its rivals. (shrink)

In previous analyses of the influence of language on cognition, speech has been the main channel examined. In studies conducted among Yucatec Mayas, efforts to determine the preferred frame of reference in use in this community have failed to reach an agreement (Bohnemeyer & Stolz, 2006; Levinson, 2003 vs. Le Guen, 2006, 2009). This paper argues for a multimodal analysis of language that encompasses gesture as well as speech, and shows that the preferred frame of reference in Yucatec (...) Maya is only detectable through the analysis of co-speech gesture and not through speech alone. A series of experiments compares knowledge of the semantics of spatial terms, performance on nonlinguistic tasks and gestures produced by men and women. The results show a striking gender difference in the knowledge of the semantics of spatial terms, but an equal preference for a geocentric frame of reference in nonverbal tasks. In a localization task, participants used a variety of strategies in their speech, but they all exhibited a systematic preference for a geocentric frame of reference in their gestures. (shrink)

This article explores “Inner Speech Account of Introspection”, according to which inner speech is the source of our introspective self-knowledge. The view hypothesizes that we come to know that we are thinking that p by being aware of the sentence of inner speech “p” accompanying the thought. I argue for Inner Speech Account by showing that it explains six explananda imposed for the philosophical theories of introspection; peculiar access, privileged access, detection condition, the lack of (...) phenomenology, occurent/dispositional distinction, and content/attitude distinction. (shrink)

Speech and music reflect extraordinary aspects of human cognitive abilities. Pitch, as an important parameter in the auditory domain, has been the focus of previous research on the relations between speech and music. The present study continues this line of research by focusing on two aspects of pitch processing: pitch prominence and melodic expectation. Specifically, we examined the perceived boundary of prominence for focus/accent in speech and music, plus the comparison between the pitch expectation patterns of music (...) and speech. Speech (Mandarin Chinese) and music stimuli were created with different interval steps that increased from 1 semitone to 12 semitones from the third to the fourth word/note of a sentence/melody. The results showed that ratings of both accent/focus and expectation/surprise increased with increasing semitone distance from the baseline (though this pattern was mixed with tonal stability profiles for the melodies). Nevertheless, the perceived boundary of prominence was different for music and speech, with the boundary for detecting prominence in speech higher than that in music. Expectation also showed different patterns for speech and music. The results thus favor the suggestion that speech prosody and music melody tend to require specialized pitch patterns unique to their own respective communication purposes. (shrink)

Two computer simulations are investigated that model interaction of cultural evolution of language and biological evolution of adaptations to language. Both are agent‐based models in which a population of agents imitates each other using realistic vowels. The agents evolve under selective pressure for good imitation. In one model, the evolution of the vocal tract is modeled; in the other, a cognitive mechanism for perceiving speech accurately is modeled. In both cases, biological adaptations to using and learning speech evolve, (...) even though the system of speech sounds itself changes at a more rapid time scale than biological evolution. However, the fact that the available acoustic space is used maximally (a self‐organized result of cultural evolution) is constant, and therefore biological evolution does have a stable target. This work shows that when cultural and biological traits are continuous, their co‐evolution may lead to cognitive adaptations that are strong enough to detect empirically. (shrink)

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 respondreactivelyto such material: offensive messages that have already been posted are reviewed by human moderators if complaints from users are received. The offensive posts are onlysubsequentlyremoved 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. (shrink)

It is well known that the unpredictable speech production brought on by stress from the task at hand has a significant negative impact on the performance of speech processing algorithms. Speech therapy benefits from being able to detect stress in speech. Speech processing performance suffers noticeably when perceptually produced stress causes variations in speech production. Using the acoustic speech signal to objectively characterize speaker stress is one method for assessing production variances brought on (...) by stress. Real-world complexity and ambiguity make it difficult for decision-makers to express their conclusions with clarity in their speech. In particular, the Neutrosophic speech algorithm is used to encode the language variables because they cannot be computed directly. Neutrosophic sets are used to manage indeterminacy in a practical situation. Existing algorithms are used except for stress on Neutrosophic speech recognition. The creation of algorithms that calculate, categorize, or differentiate between different stress circumstances. Understanding stress and developing strategies to combat its effects on speech recognition and human-computer interaction system are the goals of this recognition. (shrink)

Purpose The purpose of this paper is to present a quantitative and qualitative synthesis of the diverse academic proposals and initiatives for preventing and eliminating hate speech on the internet. Design/methodology/approach The foundation for this study is a systematic review of papers devoted to the analysis of hate speech. It has been conducted using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) protocol and applied to an initial corpus of 436 academic texts. Having implemented the suitability, (...) screening and inclusion criteria, this corpus was refined to a sample of 74 articles. Findings The main subject categories studied in this corpus of academic research are legal issues and social media. In the majority of the articles, the use of hate speech via social media is associated with five typologies: religion, cyber racism, political slurs, misogyny and attacks on the LGTBI community. The absence of ethical reflection is one of the major shortcomings of IT-focused research and analysis devoted to online hate speech. Practical implications To date various systematic reviews have been presented, and they focus on detecting or describing hate speech. These have used either the search appraisal synthesis analysis framework or the Cochrane network. The PRISMA protocol was applied for this study, and both Scopus and texts in German were included. To date no major, rigorous systematic review has been undertaken of proposals to combat hate speech. Originality/value The link between hate speech and poverty has not been studied in depth within the academic sphere. Tolerance and ethical compassion are not granted the attention they merit when it comes to analysing the phenomenon of hate speech. (shrink)

In this study, multidimensional feature extraction is performed on the U-language recordings of the test takers, and these features are evaluated separately, with five categories of features: pronunciation, fluency, vocabulary, grammar, and semantics. A deep neural network model is constructed to model the feature values to obtain the final score. Based on the previous research, this study uses a deep neural network training model instead of linear regression to improve the correlation between model score and expert score. The method of (...) using word frequency for semantic scoring is replaced by the LDA topic model for semantic analysis, which eliminates the need for experts to manually label keywords before scoring and truly automates the critique. Also, this paper introduces text cleaning after speech recognition and deep learning-based speech noise reduction technology in the scoring model, which improves the accuracy of speech recognition and the overall accuracy of the scoring model. Also, innovative applications and improvements are made to key technologies, and the latest technical solutions are integrated and improved. A new open oral grading model is proposed and implemented, and innovations are made in the method of speech feature extraction to improve the dimensionality of open oral grading. (shrink)

Causation is a core feature of human cognition and language. How children learn about intricate causal meanings is yet unresolved. Here, we focus on how children learn verbs that express causation. Such verbs, known as lexical causatives (e.g., break and raise), lack explicit morphosyntactic markers indicating causation, thus requiring that the child generalizes the causal meaning from the context. The language addressed to children presumably plays a crucial role in this learning process. Hence, we tested whether adults adapt their use (...) of lexical causatives to children when talking to them in day-to-day interactions. We analyzed naturalistic longitudinal data from 12 children in the Manchester corpus (spanning from 20 to 36 months of age). To detect semantic generalization, we employed a network approach with semantics learned from cross-situational contexts. Our results show an increasing trend in the expansion of causative semantics, observable in both child speech and child-directed speech. Adults consistently maintain somewhat more intricate causative semantic networks compared to children. However, both groups display evolving patterns. Around 28–30 months of age, children undergo a reduction in the degree of causative generalization, followed by a slightly time-lagged adjustment by adults in their speech directed to children. These findings substantiate adults' adaptation in child-directed speech, extending to semantics. They highlight child-directed speech as a highly adaptive and subconscious teaching tool that facilitates the dynamic processes of language acquisition. (shrink)

Two computer simulations are investigated that model interaction of cultural evolution of language and biological evolution of adaptations to language. Both are agent-based models in which a population of agents imitates each other using realistic vowels. The agents evolve under selective pressure for good imitation. In one model, the evolution of the vocal tract is modeled; in the other, a cognitive mechanism for perceiving speech accurately is modeled. In both cases, biological adaptations to using and learning speech evolve, (...) even though the system of speech sounds itself changes at a more rapid time scale than biological evolution. However, the fact that the available acoustic space is used maximally is constant, and therefore biological evolution does have a stable target. This work shows that when cultural and biological traits are continuous, their co-evolution may lead to cognitive adaptations that are strong enough to detect empirically. (shrink)

Emotive speech is a social act in which a speaker displays emotional signals with a specific intention; in the case of third-party complaints, this intention is to elicit empathy in the listener. The present study assessed how the emotivity of complaints was perceived in various conditions. Participants listened to short statements describing painful or neutral situations, spoken with a complaining or neutral prosody, and evaluated how complaining the speaker sounded. In addition to manipulating features of the message, social-affiliative factors (...) which could influence complaint perception were varied by adopting a cross-cultural design: participants were either Québécois (French Canadian) or French and listened to utterances expressed by both cultural groups. The presence of a complaining tone of voice had the largest effect on participant evaluations, while the nature of statements had a significant, but smaller influence. Marginal effects of culture on explicit evaluation of complaints were found. A multiple mediation analysis suggested that mean fundamental frequency was the main prosodic signal that participants relied on to detect complaints, though most of the prosody effect could not be linearly explained by acoustic parameters. These results highlight a tacit agreement between speaker and listener: what characterizes a complaint is how it is said (i.e., the tone of voice), more than what it is about or who produces it. More generally, the study emphasizes the central importance of prosody in expressive speech acts such as complaints, which are designed to strengthen social bonds and supportive responses in interactive behavior. This intentional and interpersonal aspect in the communication of emotions needs to be further considered in research on affect and communication. (shrink)

Some children may face some developmental problems in one ormore areas of their developmental milestones. One of them is speech delay. Todate, a screening tool for speech delay early detection among children is stilllacking, especially in Malaysia. Parents do not know where to refer and whichorganisation can help them especially for first-time parents. The objective ofthis paper is twofold. First, this paper analyses existing screening system orapplication for speech delay in children. Second, this paper proposes a (...) mobileapplication designed for Malaysian parents to help them detect speech delayin their children. A qualitative expert review was used to design and build theapplication. The screening application proposed is for early detection and tourge parents to seek for early intervention through appropriate assessments. Inconclusion, early detection in speech delay is critically important to increasethe chances for improving speech and communication skills. Thus, a speechdelay screening tool is needed for parents to seek proper treatment for theirchildren. (shrink)

In this article, a new adaptive data-driven strategy for voice activity detection using empirical mode decomposition is proposed. Speech data are decomposed using an a posteriori, adaptive, data-driven EMD in the time domain to yield a set of physically meaningful intrinsic mode functions. Each IMF preserves the nonlinear and nonstationary property of the speech utterance. Among a set of IMFs, the IMF that contains source information dominantly called characteristic IMF can be identified and extracted by designing a (...) zero-frequency filter-assisted peaking resonator. The detected CIMF is used to compute energy using short-term processing. Choosing proper threshold, voiced regions in speech utterances are detected using frame energy. The proposed framework has been studied on both clean speech utterance and noisy speech utterance. The proposed method is used for voice activity detection in the presence of white noise and shows encouraging result in the presence of white noise up to 0 dB. (shrink)

Considering The Third Man as an “entertainment” with “serious religious and ethical engagement,” this essay suggests the novel’s ultimate discrediting of the despair indicated by the desolate setting, postwar Vienna, and by Jansenist determinism. Two thematically crucial scenes address this despair: the visit to the office of Dr. Winkler, the cynical relic collector; and the interview between the protagonist and the charlatan Harry Lime, who has faked his own death, as they ride on the Great Wheel. “Both Lime’s speech (...) atop the Wheel and Winkler’s dismissal of the relics point the reader to the same interpretive enigma: bodies are nothing more than charnel or they are significant spiritual ‘clues.’” A comparison to the story “A Visit to Morin” shows how The Third Man forces a confrontation with the possibility of grace. (shrink)

_Objective:_ The present work aims to detect the role of the rate of speech as a mechanism able to give information on patient's intrapsychic activity and the intersubjective quality of the patient–therapist relationship. _Method:_ Thirty clinical sessions among five patients were sampled and divided into idea units ( N = 1276) according to the referential activity method. Each idea unit was rated according to referential activity method and in terms of speech rate (syllables per second) for both patient (...) and therapist. A mixed-effects model was applied in order to detect the relationship between the speech rate of both the patient and the therapist and the features of the patient's verbal production in terms of referential activity scales. A Pearson correlation was applied to evaluate the synchrony between the speech rate of the patient and the therapist. _Results:_ Results highlight that speech rate varies according patient's ability to get in touch with specific aspects detected through referential activity method: patient and the therapist speech rate get synchronized during the course of the sessions; and the therapist's speech rate partially attunes to the patient's ability to get in touch with inner aspects detected through RA method. _Conclusion:_ The work identified speech rate as a feature that may help in the development of the clinical process in light of its ability to convey information about a patient's internal states and a therapist's attunement ability. These results support the intersubjective perspective on the clinical process. (shrink)

Lip reading is the ability to partially understand speech by looking at the speaker's lips. It improves the intelligibility of speech in noise when audio-visual perception is compared with audio-only perception. A recent set of experiments showed that seeing the speaker's lips also enhances sensitivity to acoustic information, decreasing the auditory detection threshold of speech embedded in noise [J. Acoust. Soc. Am. 109 (2001) 2272; J. Acoust. Soc. Am. 108 (2000) 1197]. However, detection is different (...) from comprehension, and it remains to be seen whether improved sensitivity also results in an intelligibility gain in audio-visual speech perception. In this work, we use an original paradigm to show that seeing the speaker's lips enables the listener to hear better and hence to understand better. The audio-visual stimuli used here could not be differentiated by lip reading per se since they contained exactly the same lip gesture matched with different compatible speech sounds. Nevertheless, the noise-masked stimuli were more intelligible in the audio-visual condition than in the audio-only condition due to the contribution of visual information to the extraction of acoustic cues. Replacing the lip gesture by a non-speech visual input with exactly the same time course, providing the same temporal cues for extraction, removed the intelligibility benefit. This early contribution to audio-visual speech identification is discussed in relationships with recent neurophysiological data on audio-visual perception. (shrink)

The performance of most of the state-of-the-art speaker recognition systems deteriorates under degraded conditions, owing to mismatch between the training and testing sessions. This study focuses on the front end of the speaker verification system to reduce the mismatch between training and testing. An adaptive voice activity detection algorithm using zero-frequency filter assisted peaking resonator was integrated into the front end of the SV system. The performance of this proposed SV system was studied under degraded conditions with 50 selected (...) speakers from the NIST 2003 database. The degraded condition was simulated by adding different types of noises to the original speech utterances. The different types of noises were chosen from the NOISEX-92 database to simulate degraded conditions at signal-to-noise ratio levels from 0 to 20 dB. In this study, widely used 39-dimension Mel frequency cepstral coefficient features were used, and Gaussian mixture model–universal background model was used for speaker modeling. The proposed system’s performance was studied against the energy-based VAD used as the front end of the SV system. The proposed SV system showed some encouraging results when EMD-based VAD was used at its front end. (shrink)

The relationship between the neurobiology of speech and music has been investigated for more than a century. There remains no widespread agreement regarding how (or to what extent) music perception utilizes the neural circuitry that is engaged in speech processing, particularly at the cortical level. Prominent models such as Patel’s Shared Syntactic Integration Resource Hypothesis (SSIRH) and Koelsch’s neurocognitive model of music perception suggest a high degree of overlap, particularly in the frontal lobe, but also perhaps more distinct (...) representations in the temporal lobe with hemispheric asymmetries. The present meta-analysis study used activation likelihood estimate analyses to identify the brain regions consistently activated for music as compared to speech across the functional neuroimaging (fMRI and PET) literature. Eighty music and 91 speech neuroimaging studies of healthy adult control subjects were analyzed. Peak activations reported in the music and speech studies were divided into four paradigm categories: passive listening, discrimination tasks, error/anomaly detection tasks and memory-related tasks. We then compared activation likelihood estimates within each category for music versus speech, and each music condition with passive listening. We found that listening to music and to speech preferentially activate distinct temporo-parietal bilateral cortical networks. We also found music and speech to have shared resources in the left pars opercularis but speech-specific resources in the left pars triangularis. The extent to which music recruited speech-activated frontal resources was modulated by task. While there are certainly limitations to meta-analysis techniques particularly regarding sensitivity, this work suggests that the extent of shared resources between speech and music may be task-dependent and highlights the need to consider how task effects may be affecting conclusions regarding the neurobiology of speech and music. (shrink)

We introduce a novel paradigm for studying the cognitive processes used by listeners within interactive settings. This paradigm places the talker and the listener in the same physical space, creating opportunities for investigations of attention and comprehension processes taking place during interactive discourse situations. An experiment was conducted to compare results from previous research using videotaped stimuli to those obtained within the live face-to-face task paradigm. A headworn apparatus is used to briefly display LEDs on the talker’s face in four (...) locations as the talker communicates with the participant. In addition to the primary task of comprehending speeches, participants make a secondary task light detection response. In the present experiment, the talker gave non-emotionally-expressive speeches that were used in past research with videotaped stimuli. Signal detection analysis was employed to determine which areas of the face received the greatest focus of attention. Results replicate previous findings using videotaped methods. (shrink)

Hearing loss in old age, which often goes untreated, has far-reaching consequences. Furthermore, reduction of cognitive abilities and dementia can also occur, which also affects quality of life. The aim of this study was to investigate the hearing performance of seniors without hearing complaints with respect to speech perception in noise and the ability to localize sounds. Results were tested for correlations with age and cognitive performance. The study included 40 subjects aged between 60 and 90 years with not (...) self-reported hearing problems. The subjects were screened for dementia. Audiological tests included pure-tone audiometry and speech perception in two types of background noise which was either co-located or spatially separated from the target speech. Sound localization ability was assessed and hearing performance was self-evaluated by a questionnaire. Speech in noise and sound localization was compared with young normal hearing adults. Although considering themselves as hearing normal, 17 subjects had at least a mild hearing loss. There was a significant negative correlation between hearing loss and dementia screening score. Speech perception in noise decreased significantly with age. There were significant negative correlations between speech perception in noise and DemTect score for both spatial configurations. Mean SRTs obtained in the co-located noise condition with amplitude-modulated noise were on average 3.1 dB better than with continuous noise. This gap-listening effect was severely diminished compared to a younger normal hearing subject group. In continuous noise, spatial separation of speech and noise led to better SRTs compared to the co-located masker condition. SRTs in MSNF deteriorated in modulated noise compared to continuous noise by 2.6 dB. Highest impact of age was found for speech perception scores using noise stimuli with temporal modulation in binaural test conditions. Mean localization error was in the range of young adults. Mean amount of front/back confusions was 11.5% higher than for young adults. Speech perception tests in the presence of temporally modulated noise can serve as a screening method for early detection of hearing disorders in older adults. This allows for early prescription of hearing aids. (shrink)

Dementia, a prevalent disorder of the brain, has negative effects on individuals and society. This paper concerns using Spontaneous Speech Challenge of Interspeech 2020 to classify Alzheimer's dementia. We used VGGish, a deep, pretrained, Tensorflow model as an audio feature extractor, and Scikit-learn classifiers to detect signs of dementia in speech. Three classifiers were 59.1% accurate, which was 3% above the best-performing baseline models trained on the acoustic features used in the challenge. We also proposed DemCNN, a new (...) PyTorch raw waveform-based convolutional neural network model that was 63.6% accurate, 7% more accurate then the best-performing baseline linear discriminant analysis model. We discovered that audio transfer learning with a pretrained VGGish feature extractor performs better than the baseline approach using automatically extracted acoustic features. Our DepCNN exhibits good generalization capabilities. Both methods presented in this paper offer progress toward new, innovative, and more effective computer-based screening of dementia through spontaneous speech. (shrink)

The most prominent form of human communication and interaction is speech. It plays an indispensable role for expressing emotions, motivating, guiding, and cheering. An ill-intentioned speech can mislead people, societies, and even a nation. A misguided speech can trigger social controversy and can result in violent activities. Every day, there are a lot of speeches being delivered around the world, which are quite impractical to inspect manually. In order to prevent any vicious action resulting from any misguided (...) speech, the development of an automatic system that can efficiently detect suspicious speech has become imperative. In this study, we have presented a framework for acquisition of speech along with the location of the speaker, converting the speeches into texts and, finally, we have proposed a system based on long short-term memory which is a variant of recurrent neural network to classify speeches into suspicious and nonsuspicious. We have considered speeches of Bangla language and developed our own dataset that contains about 5000 suspicious and nonsuspicious samples for training and validating our model. A comparative analysis of accuracy among other machine learning algorithms such as logistic regression, SVM, KNN, Naive Bayes, and decision tree is performed in order to evaluate the effectiveness of the system. The experimental results show that our proposed deep learning-based model provides the highest accuracy compared to other algorithms. (shrink)

Alzheimer's Disease is a form of dementia that affects the memory, cognition, and motor skills of patients. Extensive research has been done to develop accessible, cost-effective, and non-invasive techniques for the automatic detection of AD. Previous research has shown that speech can be used to distinguish between healthy patients and afflicted patients. In this paper, the ADReSS dataset, a dataset balanced by gender and age, was used to automatically classify AD from spontaneous speech. The performance of five (...) classifiers, as well as a convolutional neural network and long short-term memory network, was compared when trained on audio features and text features. The same audio and text features were used to train five regression models to predict the Mini-Mental State Examination score for each patient, a score that has a maximum value of 30. The top-performing classification models were the support vector machine and random forest classifiers trained on BERT embeddings, which both achieved an accuracy of 85.4% on the test set. The best-performing regression model was the gradient boosting regression model trained on BERT embeddings and CLAN features, which had a root mean squared error of 4.56 on the test set. The performance on both tasks illustrates the feasibility of using speech to classify AD and predict neuropsychological scores. (shrink)

The global array might prove to be an important and even necessary concept for explaining some multi-modal phenomena from the specificational perspective. However, we suspect that specification exists in energy arrays detectable by single or multiple sensory systems. We argue for a more general modality-neutral perspective and review results from recent research on audiovisual speech perception.

In the process of communication between people, everyone will have emotions, and different emotions will have different effects on communication. With the help of external performance information accompanied by emotional expression, such as emotional speech signals or facial expressions, people can easily communicate with each other and understand each other. Emotion recognition is an important network of affective computers and research centers for signal processing, pattern detection, artificial intelligence, and human-computer interaction. Emotions convey important information in human communication (...) and communication. Since the end of the last century, people have started the research on emotion recognition, especially how to correctly judge the emotion type has invested a lot of time and energy. In this paper, multi-modal emotion recognition is introduced to recognize facial expressions and speech, and conduct research on adaptive higher education management. Language and expression are the most direct ways for people to express their emotions. After obtaining the framework of the dual-modal emotion recognition system, the BOW model is used to identify the characteristic movement of local areas or key points. The recognition rates of emotion recognition for 1,000 audios of anger, disgust, fear, happiness, sadness and surprise are: 97.3, 83.75, 64.87, 89.87, 84.12, and 86.68%, respectively. (shrink)

Job seekers find themselves increasingly duped and misled by fraudulent job advertisements, posing a threat to their privacy, security and well-being. There is a clear need for solutions that can protect innocent job seekers. Existing approaches to detecting fraudulent jobs do not scale well, function like a black-box, and lack interpretability, which is essential to guide applicants’ decision-making. Moreover, commonly used lexical features may be insufficient as the representation does not capture contextual semantics of the underlying document. Hence, this paper (...) explores to what extent different categorizations of fraudulent jobs can be classified. In addition, this paper seeks to find what type of features are most relevant in classifying the type of fraudulent job. In this paper, we develop and validate a machine learning system for identifying identity theft, corporate identity theft and multi-level marketing amongst fraudulent job advertisements. We utilized four classes of features: empirical rule set-based features, bag-of-word models, most recent state-of-the-art word embeddings and transformer models for various machine learning classifiers. The machine learning models were validated by evaluating them on a publicly available job description dataset. Our results indicate that the word embeddings and transformer-based features consistently outperformed the handcrafted rule-set based features class. Ultimately, a Gradient Boosting classifier with a combination of empirical rule-set based features, parts-of-speech tags and bag-of-words vectors achieved the best performance with an F1-score of 0.88. (shrink)

The primary focus of this project is the silent and subvocal speech-recognition interface unveiled in 2018 as an ambulatory device wearable on the neck that detects a myoelectrical signature by electrodes worn on the surface of the face, throat, and neck. These emerge from an alleged “intending to speak” by the wearer silently-saying-something-to-oneself. This inner voice is believed to occur while one reads in silence or mentally talks to oneself. The artifice does not require spoken sounds, opening the mouth, (...) or any explicit or external movement of the lips. The essay then considers such subvocal “speech” as a mode of writing or saying and the interior of the mouth or oral cavity as its writing surface. It briefly revisits discussions of telepathy to recontextualize Heidegger’s warning against enframing language exclusively within calculative technics and physiology, which he suggests is detrimental to Mundarten (mouth-modes of regional dialects). It closes in reconsideration of Husserl’s phenomenology of language and meaning in Ideas as it might apply to subvocal speech-recognition interfaces. It suggests ways by which the electrophysiology that the device detects and deciphers (as an alleged intention of a presumed natural language unspoken vocally or aloud) might supplement Husserl’s insinuation of the Leiblichkeit of language through a self-stamping extraction of an extension of meaning. (shrink)

When infants and toddlers are confronted with sequences of sounds, they are required to segment the sounds into meaningful units to achieve sufficient understanding. Rhythm has been regarded as a crucial cue for segmentation of speech sounds. Although previous intermodal methods indicated that infants and toddlers could detect differences in speech sounds based on stress-timed and syllable-timed units, these methods could not clearly indicate how infants and toddlers perform sound segmentation. Thus, the present study examined whether Japanese infants (...) and toddlers could segment word speech sounds comprising basic morae, on the basis of concurrent basic mora units within syllable units, using the new intermodal matching procedure. The results indicated that, regardless of their ages and linguistic abilities, Japanese infants and toddlers aged 6–25 months tended to segment Japanese words comprising basic morae sounds on the basis of concurrent basic mora units within syllable units. This implies that infants' and toddlers' use of syllable units for segmentation of speech sounds at an early age could be evident among many infants and toddlers learning various languages. Although this finding should be interpreted carefully, the present study demonstrated the utility of the new intermodal matching procedure for examining segmentation of speech sounds and word sounds by infants and toddlers, on the basis of specific rhythm units. (shrink)

In this paper, we describe the challenges of collecting data in the Māori population for automatic detection of schizophrenia using natural language processing (NLP). Existing psychometric tools for detecting are wide ranging and do not meet the health needs of indigenous persons considered at risk of developing psychosis and/or schizophrenia. Automated methods using NLP have been developed to detect psychosis and schizophrenia but lack cultural nuance in their designs. Research incorporating the cultural aspects relevant to indigenous communities is lacking (...) in the design of existing automatic prediction tools and one of the main reasons is the scarcity of data from indigenous populations. This paper explores the current design of the New Zealand health care system and its potential impacts on access and inequities in the Māori population and details the methodology used to collect speech samples of Māori at risk of developing psychosis and schizophrenia. The paper also describes the major obstacles faced during speech data collection, key findings, and probable solutions. (shrink)

Emotional recognition has arisen as an essential field of study that can expose a variety of valuable inputs. Emotion can be articulated in several means that can be seen, like speech and facial expressions, written text, and gestures. Emotion recognition in a text document is fundamentally a content-based classification issue, including notions from natural language processing (NLP) and deep learning fields. Hence, in this study, deep learning assisted semantic text analysis (DLSTA) has been proposed for human emotion detection (...) using big data. Emotion detection from textual sources can be done utilizing notions of Natural Language Processing. Word embeddings are extensively utilized for several NLP tasks, like machine translation, sentiment analysis, and question answering. NLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text. The numerical outcomes demonstrate that the suggested method achieves an expressively superior quality of human emotion detection rate of 97.22% and the classification accuracy rate of 98.02% with different state-of-the-art methods and can be enhanced by other emotional word embeddings. (shrink)

Introduction: Motherese, or emotional infant directed speech, is the specific form of speech used by parents to address their infants. The prosody of IDS has affective properties, expresses caregiver involvement, is a marker of caregiver-infant interaction quality. IDS prosodic characteristics can be detected with automatic analysis. We aimed to explore whether pregnant women “speak” to their unborn baby, whether they use motherese while speaking and whether anxio-depressive or obstetrical status impacts speaking to the fetus.Participants and Methods: We conducted (...) an observational study of pregnant women with gestational ages from 26 to 38 weeks. Women were recruited in a university hospital department of obstetrics. Thirty-five women agreed to participate in the study, and 26 audio records were exploitable. We collected obstetrical and sociodemographic data, pregnancy outcomes, anxiety and depressive status using the Covy and Raskin Scales, and life events using the Sensations During Pregnancy and Life Event Questionnaire. Each participant was left alone with an audio recorder with a recommendation to feel free to speak to her fetus as she would have done at home. The recording was stopped after 3 min. Audio recordings were analyzed by two methods: psycholinguist experts' annotation and computational objective automatic analyses.Results: Most mothers reported speaking to their fetuses. We found a correlation between maternal first perceptions of fetal movements and the start of mother's speaking to fetus. Motherese prosody was detected with both annotation and automatic analysis with a significant correlation between the two methods. In this exploratory study, motherese use was not associated with maternal anxiodepressive or obstetrical status. However, the more future mothers were depressed, the less they spoke with their fetuses during the recording.Conclusion: Fetal directed speech can be detected during pregnancy, and it contains a period of prosody that shares the same characteristics of motherese that can be described as prenatal motherese or emotional fetal-directed speech. This means that pregnant women start using motherese much earlier than expected. FDS seems to be correlated with maternal first perceptions of fetal movements and depression scores. However, more research is needed to confirm these exploratory results. (shrink)

This experimental study sets out to determine whether people detect click sounds in American English. Recent research has documented the use of non-phonemic clicks in a variety of languages to fulfill a range of functions such as sequence management or signaling searches and different types of attitudinal stance. While these clicks are acoustically salient and have been reported to occur with a frequency of up to 14 per minute in British English, they have not been widely investigated until relatively recently. (...) For this experiment, we designed video stimuli consisting of A and B pairs of approximately 10 seconds of speech, one with a click and the other with the click edited out. We gave 118 participants a questionnaire and asked if they could detect a difference between the pairs of videos. The results indicate that the majority of participants, between 79% and 86%, do not detect click sounds. (shrink)

Speech is a primary means of human communication and one of the most basic features of human conduct. Voice is an important part of its subsystems. A speech disorder is a condition that affects the ability of a person to speak normally, which occasionally results in voice impairment with psychological and emotional consequences. Early detection of voice problems is a crucial factor. Computer-based procedures are less costly and easier to administer for such purposes than traditional methods. This (...) study highlights the following issues: recent studies, methods of voice pathology detection, machine learning and deep learning (DL) methods used in data classification, main datasets utilized, and the role of Internet of things (IoT) systems employed in voice pathology diagnosis. Moreover, this study presents different applications, open challenges, and recommendations for future directions of IoT systems and artificial intelligence (AI) approaches in the voice pathology diagnosis. Finally, this study highlights some limitations of voice pathology datasets in comparison with the role of IoT in the healthcare sector, which shows the urgent need to provide efficient approaches and easy and ideal medical diagnostic procedures and treatments of disease identification for doctors and patients. This review covered voice pathology taxonomy, detection techniques, open challenges, limitations, and recommendations for future directions to provide a clear background for doctors and patients. Standard databases, including the Massachusetts Eye and Ear Infirmary, Saarbruecken Voice Database, and the Arabic Voice Pathology Database, were used in most articles reviewed in this article. The classes, features, and main purpose for voice pathology identification are also highlighted. This study focuses on the extraction of voice pathology features, especially speech analysis, extends feature vectors comprising static and dynamic features, and converts these extended feature vectors into solid vectors before passing them to the recognizer. (shrink)

We explore whether children’s willingness to produce unfamiliar sequences of words reflects their experience with similar lexical patterns. We asked children to repeat unfamiliar sequences that were identical to familiar phrases (e.g.,A piece of toast) but for one word (e.g., a novel instantiation ofA piece ofX, likeA piece of brick). We explore two predictions—motivated by findings in the statistical learning literature—that children are likely to have detected an opportunity to substitute alternative words into the final position of a four‐word sequence (...) if (a) it is difficult to predict the fourth word given the first three words and (b) the words observed in the final position are distributionally similar. Twenty‐eight 2‐year‐olds and thirty‐one 3‐year‐olds were significantly more likely to correctly repeat unfamiliar variants of patterns for which these properties held. The results illustrate how children’s developing language is shaped by linguistic experience. (shrink)

The article is devoted to the formation of linguistic, communicative and cultural competence among students bilinguals in teaching Russian language and speech culture. The authors put forward the thesis that the training of specialists in the conditions of bilingualism re quires not only a higher level of learning a second language, but also a qualitatively different level of comprehension. It is proved that the discipline ‘Russian and the culture of speech‘ assumes formation of communicative and culturological competence of (...) the higher education institutions, which are trained on two-profile offices taking into account a regional component. Relevance of research in this area is increasing each year since the treatment of the person as the center of all systems of cognition highlights in the pedagogical University the formation of the modern language personality, capable of effective professional activity. The functional approach provides detection of features of functioning of language units in different spheres of public work. The communicative principle means that acquisition of Russian as a means of communication happens in the course of speech practice most approached to process of communication in Russian. The detection of similarity and distinctions between languages, interlingual comparison promotes establishment and a lexical interference. The linguistic-cultural principle provides understanding of language as the phenomena of culture and is connected with ability to define national-cultural components of linguistic units - words, phraseological combinations, grammatical categories of the text. Involvement of regional component as a basis in practice of teaching Russian and culture of speech increases efficiency of all process of training of students of national branch. (shrink)