Speech stress recognition using semi-eager learning

Homo-sapiens suffer from psychogenic pain due to current day lifestyle. According to psychologists, stress is the most destructive form of psychalgia and it is a vicious companion for this species. Immoderate levels of stress may lead to the death of many individuals. Normally, the presence of stress gives rise to certain emotions which can be detected to predict stress levels of a person. This paper proposes the development of mechanized and efficient Speech Emotion Recognition (SER) for stress level analysis. The paper investigates the performance of perceptual based speech features like Revised Perceptual Linear Prediction Coefficients, Bark Frequency Cepstral Coefficients, Perceptual Linear Predictive Cepstrum, Gammatone Frequency Cepstral coefficient, Mel Frequency Cepstral Coefficient, Gammatone Wavelet Cepstral Coefficient and Inverted Mel Frequency Cepstral Coefficients on SER. The novelty of this work involves application of a SemiEager (SemiE) learning algorithm for evaluating auditory cues. SemiE offers advantages over eager and lazy based learning by reducing the computational cost. Stress level recognition being the main objective, the Speech Under Simulated and Actual Stress (SUSAS) benchmark database is used for performance analysis. A comparative analysis is presented to demonstrate the improvement in the SED performance. An overall accuracy of 90.66% recognition of stress related emotions is achieved.     

Lexical representations are malleable for about one second: Evidence for the non-automaticity of perceptual recalibration

In listening to speech, people have been shown to apply several types of adjustment to their phonemic categories that take into account variations in the prevailing linguistic environment. These adjustments include selective adaptation, lexically driven recalibration, and audiovisually determined recalibration. Prior studies have used dual task procedures to test whether these adjustments are automatic or if they require attention, and all of these tests have supported automaticity. The current study instead uses a method of targeted distraction to demonstrate that lexical recalibration does in fact require attention. Building on this finding, the targeted distraction method is used to measure the period of time during which the lexical percept remains malleable. The results support a processing window of approximately one second, consistent with the results of a small number of prior studies that bear on this question. The results also demonstrate that recalibration is closely linked to the completion of lexical access.     

Characterizing perceptual learning with external noise

Performance in perceptual tasks often improves with practice. This effect is known as ‘perceptual learning,’ and it has been the source of a great deal of interest and debate over the course of the last century. Here, we consider the effects of perceptual learning within the context of signal detection theory. According to signal detection theory, the improvements that take place with perceptual learning can be due to increases in internal signal strength or decreases in internal noise. We used a combination of psychophysical techniques (external noise masking and double-pass response consistency) that involve corrupting stimuli with externally added noise to discriminate between the effects of changes in signal and noise as observers learned to identify sets of unfamiliar visual patterns. Although practice reduced thresholds by as much as a factor of 14, internal noise remained virtually fixed throughout training, indicating learning served to predominantly increase the strength of the internal signal. We further examined the specific nature of the changes that took place in signal strength by correlating the externally added noise with observer’s decisions across trials (response classification). This technique allowed us to visualize some of the changes that took place in the linear templates used by the observers as learning occurred, as well as test the predictions of a linear template-matching model. Taken together, the results of our experiments offer important new theoretical constraints on models of perceptual learning.     

Examining the robustness of the relationship between metacognitive efficiency and metacognitive bias

We recently found a positive relationship between estimates of metacognitive efficiency and metacognitive bias. However, this relationship was only examined on a within-subject level and required binarizing the confidence scale, a technique that introduces methodological difficulties. Here we examined the robustness of the positive relationship between estimates of metacognitive efficiency and metacognitive bias by conducting two different types of analyses. First, we developed a new within-subject analysis technique where the original n-point confidence scale is transformed into two different (n-1)-point scales in a way that mimics a naturalistic change in confidence. Second, we examined the across-subject correlation between metacognitive efficiency and metacognitive bias. Importantly, for both types of analyses, we not only established the direction of the effect but also computed effect sizes. We applied both techniques to the data from three tasks from the Confidence Database (N > 400 in each). We found that both approaches revealed a small to medium positive relationship between metacognitive efficiency and metacognitive bias. These results demonstrate that the positive relationship between metacognitive efficiency and metacognitive bias is robust across several analysis techniques and datasets, and have important implications for future research.     

Binocular vision in infancy: Responsiveness to uncrossed horizontal disparity

This research explored the onset of stereopsis, the ability to perceive depth from the different views provided by the two eyes. In a longitudinal study, infants were tested weekly from 6 to 20 weeks of age. The primary goal of the study was to establish the onset and the early development of sensitivity to uncrossed horizontal disparity. The infant participants were shown dynamic random dot stereograms displaying two squares, one with uncrossed horizontal disparity (0.5°) and one with vertical disparity (0.5°). The stimuli were presented on an autostereoscopic monitor. We used two methods, the forced-choice preferential looking (FPL) method and the classical natural preference (CNP) method, to measure whether the infants preferred the uncrossed over the vertical disparity display. According to the FPL data, the mean relative preferences for horizontal over vertical disparity were significantly greater than chance probability (0.50) from 13 weeks of age onward. With the CNP method we found significant preferences for uncrossed horizontal disparity from 15 weeks onward. The FPL method was hence more sensitive than the CNP method as it indicated an earlier onset of responsiveness to stereoscopic information.     

Sequence-sensitive exemplar and decision-bound accounts of speeded-classification performance in a modified Garner-tasks paradigm

Among the most fundamental results in the area of perceptual classification are the “correlated facilitation” and “filtering interference” effects observed in Garner’s (1974) speeded categorization tasks: In the case of integral-dimension stimuli, relative to a control task, single-dimension classification is faster when there is correlated variation along a second dimension, but slower when there is orthogonal variation that cannot be filtered out (e.g., by attention). These fundamental effects may result from participants’ use of a trial-by-trial bypass strategy in the control and correlated tasks: The observer changes the previous category response whenever the stimulus changes, and maintains responses if the stimulus repeats. Here we conduct modified versions of the Garner tasks that eliminate the availability of a pure bypass strategy. The fundamental facilitation and interference effects remain, but are still largely explainable in terms of pronounced sequential effects in all tasks. We develop sequence-sensitive versions of exemplar-retrieval and decision-bound models aimed at capturing the detailed, trial-by-trial response-time distribution data. The models combine assumptions involving: (i) strengthened perceptual/memory representations of stimuli that repeat across consecutive trials, and (ii) a bias to change category responses on trials in which the stimulus changes. These models can predict our observed effects and provide a more complete account of the underlying bases of performance in our modified Garner tasks.     

Parts of me: Identity-relevance moderates self-prioritization

Recent research has revealed a pervasive bias for self-relevant information during decision-making, a phenomenon termed the self-prioritization effect. Focusing almost exclusively on between-target (e.g., self vs. friend) differences in task performance, however, this work has overlooked the influence stimulus factors potentially exert during decisional processing. Accordingly, based on pertinent social-psychological theorizing (i.e., Identity-Based Motivation Theory), here we explored the possibility that self-prioritization is sensitive to the identity-based relevance of stimuli. The results of three experiments supported this hypothesis. In a perceptual-matching task, stimulus enhancement was greatest when geometric shapes were associated with identity-related information that was important (vs. unimportant) to participants. In addition, hierarchical drift-diffusion modeling revealed this effect was underpinned by differences in the efficiency of visual processing. Specifically, evidence was extracted more rapidly from stimuli paired with consequential compared to inconsequential identity-related components. These findings demonstrate how identity-relevance moderates self-prioritization.     

One version of direct response priming requires automatization of the relevant associations but not awareness of the prime

Priming is the influence of one event on performance during a second event. One type of priming is known as semantic priming because it biases interpretation of the subsequent stimulus. Another type, direct response priming, biases responding directly without semantic mediation. Research reviewed in this article indicates that two versions of the second type, direct response priming, can be distinguished. One version, explicit priming, requires awareness of the prime. The other version, associative response priming, occurs even if the prime is masked and not phenomenally visible. This version, which is attributed to associations relating specific sensory events to movements of particular muscles, is enabled only if the association has previously been automatized by brief practice in which the to-be-primed response is made to the stimulus that subsequently appears as the prime. Associative response priming can be explained by a simple stimulus–response interpretation; other varieties of priming are more theoretically challenging.     

Can the Media Help Women Be Better at Math? Stereotype Threat,Selective Exposure,Media Effects,and Women's Math Performance

This study examines women's media selections when under the gender–math stereotype threat and the subsequent media effects on their math performance through the lens of the Selective Exposure Self‐ and Affect‐Management (SESAM) model, mood management theory, and social comparison theory. Female college students were randomly assigned to the stereotype threat condition or the control condition; then, they selectively browsed magazine pages showing female role models in stereotypical domains (beauty or family) and counterstereotypical domains (career or science) before taking the math test. The results show that women spent more time on career magazines when under threat, and this selective exposure's effect on their math performance was moderated by their assimilation to the role models.