Acoustic features from speech as markers of depressive and manic symptoms in bipolar disorder: A prospective study.

INTRODUCTION: Voice features could be a sensitive marker of affective state in bipolar disorder (BD). Smartphone apps offer an excellent opportunity to collect voice data in the natural setting and become a useful tool in phase prediction in BD. AIMS OF THE STUDY: We investigate the relations between the symptoms of BD, evaluated by psychiatrists, and patients' voice characteristics. A smartphone app extracted acoustic parameters from the daily phone calls of n = 51 patients. We show how the prosodic, spectral, and voice quality features correlate with clinically assessed affective states and explore their usefulness in predicting the BD phase. METHODS: A smartphone app (BDmon) was developed to collect the voice signal and extract its physical features. BD patients used the application on average for 208 days. Psychiatrists assessed the severity of BD symptoms using the Hamilton depression rating scale -17 and the Young Mania rating scale. We analyze the relations between acoustic features of speech and patients' mental states using linear generalized mixed-effect models. RESULTS: The prosodic, spectral, and voice quality parameters, are valid markers in assessing the severity of manic and depressive symptoms. The accuracy of the predictive generalized mixed-effect model is 70.9%-71.4%. Significant differences in the effect sizes and directions are observed between female and male subgroups. The greater the severity of mania in males, the louder (ß = 1.6) and higher the tone of voice (ß = 0.71), more clearly (ß = 1.35), and more sharply they speak (ß = 0.95), and their conversations are longer (ß = 1.64). For females, the observations are either exactly the opposite-the greater the severity of mania, the quieter (ß = -0.27) and lower the tone of voice (ß = -0.21) and less clearly (ß = -0.25) they speak - or no correlations are found (length of speech). On the other hand, the greater the severity of bipolar depression in males, the quieter (ß = -1.07) and less clearly they speak (ß = -1.00). In females, no distinct correlations between the severity of depressive symptoms and the change in voice parameters are found. CONCLUSIONS: Speech analysis provides physiological markers of affective symptoms in BD and acoustic features extracted from speech are effective in predicting BD phases. This could personalize monitoring and care for BD patients, helping to decide whether a specialist should be consulted.

The Role of Selected Speech Signal Characteristics in Discriminating Unipolar and Bipolar Disorders.

OBJECTIVE: The objective of this study is to explore and enhance the diagnostic process of unipolar and bipolar disorders. The primary focus is on leveraging automated processes to improve the accuracy and accessibility of diagnosis. The study aims to introduce an audio corpus collected from patients diagnosed with these disorders, annotated using the Clinical Global Impressions Scale (CGI) by psychiatrists. METHODS AND PROCEDURES: Traditional diagnostic methods rely on the clinician's expertise and consideration of co-existing mental disorders. However, this study proposes the implementation of automated processes in the diagnosis, providing quantitative measures and enabling prolonged observation of patients. The paper introduces a speech signal pipeline for CGI state classification, with a specific focus on selecting the most discriminative features. Acoustic features such as prosodies, MFCC, and LPC coefficients are examined in the study. The classification process utilizes common machine learning methods. RESULTS: The results of the study indicate promising outcomes for the automated diagnosis of bipolar and unipolar disorders using the proposed speech signal pipeline. The audio corpus annotated with CGI by psychiatrists achieved a classification accuracy of 95% for the two-class classification. For the four- and seven-class classifications, the results were 77.3% and 73%, respectively, demonstrating the potential of the developed method in distinguishing different states of the disorders.

Ambiguous at the second sight: Mixed facial expressions trigger late electrophysiological responses linked to lower social impressions.

Social interactions require quick perception, interpretation, and categorization of faces, with facial features offering cues to emotions, intentions, and traits. Importantly, reactions to faces depend not only on their features but also on their processing fluency, with disfluent faces suffering social devaluation. The current research used electrophysiological (EEG) and behavioral measures to explore at what processing stage and under what conditions emotional ambiguity is detected in the brain and how it influences trustworthiness judgments. Participants viewed male and female faces ranging from pure anger, through mixed expressions, to pure happiness. They categorized each face along the experimental dimension (happy vs. angry) or a control dimension (gender). In the emotion-categorization condition, mixed (ambiguous) expressions were classified relatively slower, and their trustworthiness was rated relatively lower. EEG analyses revealed that early brain responses are independent of the categorization condition, with pure faces evoking larger P1/N1 responses than mixed expressions. Some late (728- 880 ms) brain responses from central-parietal sites also were independent of the categorization condition and presumably reflect familiarity of the emotion categories, with pure expressions evoking larger central-parietal LPP amplitude than mixed expressions. Interestingly, other late responses were sensitive to both expressive features and categorization task, with ambiguous faces evoking a larger LPP amplitude in frontal-medial sites around 560-660 ms but only in the emotion categorization task. Critically, these late responses from the frontal-medial cluster correlated with the reduction in trustworthiness judgments. Overall, the results suggest that ambiguity detection involves late, top-down processes and that it influences important social impressions.

Mixed matters: fluency impacts trust ratings when faces range on valence but not on motivational implications.

Facial features that resemble emotional expressions influence key social evaluations, including trust. Here, we present four experiments testing how the impact of such expressive features is qualified by their processing difficulty. We show that faces with mixed expressive features are relatively devalued, and faces with pure expressive features are relatively valued. This is especially true when participants first engage in a categorisation task that makes processing of mixed expressions difficult and pure expressions easy. Critically, we also demonstrate that the impact of categorisation fluency depends on the specific nature of the expressive features. When faces vary on valence (i.e. sad to happy), trust judgments increase with their positivity, but also depend on fluency. When faces vary on social motivation (i.e. angry to sad), trust judgments increase with their approachability, but remain impervious to disfluency. This suggests that people intelligently use fluency to make judgments on valence-relevant judgment dimensions - but not when faces can be judged using other relevant criteria, such as motivation. Overall, the findings highlight that key social impressions (like trust) are flexibly constructed from inputs related to stimulus features and processing experience.

Frontal EEG alpha band asymmetry as a predictor of reasoning deficiency in depressed people.

Cognitive deficits in depression are mostly apparent in executive functions, especially when integration of information and reasoning is required. In parallel, there are also numerous studies pointing to the frontal alpha band asymmetry as a psychophysiological marker of depression. In this study, we explored the role of frontal alpha asymmetry as a potential factor explaining the cognitive problems accompanying depression. Twenty-six depressed and 26 control participants completed a reasoning task and underwent 5 minutes of electroencephalography recording. In line with the previous studies, depressed people showed difficulties with reasoning but we did not observe the relationship between frontal asymmetry in the alpha band and depression. However, we found that in the depressed group the frontal alpha asymmetry index was characterised by larger variance than in the control group, and it was also a strong predictor of cognitive functioning exclusively in the depressed group. Our results point to the disruption of a psychophysiological balance, reflected in changed frontal alpha asymmetry (into more left-sided frontal asymmetry in the alpha band, reflecting more right-sided cortical activity) as a possible brain correlate of cognitive disturbances present in depressive disorders.

From disgust to contempt-speech: The nature of contempt on the map of prejudicial emotions.

Analyzing the contempt as an intergroup emotion, we suggest that contempt and anger are not built upon each other, whereas disgust seems to be the most elementary and specific basic-emotional antecedent of contempt. Concurring with Gervais & Fessler, we suggest that many instances of "hate speech" are in fact instances of "contempt speech" - being based on disgust-driven contempt rather than hate.

Facing the edible. The effects of edibility information on the neural encoding of animal faces.

Animals perceived as edible are often denied more complex mental capacities or emotions. The process of categorizing and perceiving edible species as distant from humans has been extensively studied on the level of deliberate judgments of animals and humans. In the present study we wanted to determine whether information about the edibility of an artificially created species can affect one of the most automatic processes in humanity ascription: face perception. We focused on early perceptual stages of face processing as manifested in EEG signals by N170 Event Related Potentials. In an experimental study participants were assigned into two conditions, in which they were presented a series of human-animal morphed images. In one of the conditions participants were informed that the images present an edible species. Additionally, we measured participant judgments of the animals' capacity to suffer. Animal faces, which were perceived as non-edible, elicited larger N170 amplitudes than edible animal faces, suggesting that people recognize faces of non-edible animals as a face to a greater extent than edible ones. Importantly, this effect was significant only for those participants who perceived animals' capacity to suffer as relatively low. We discuss the obtained effects as a primary evidence for the very basic and automatic character of the "meat paradox", visible already in the initial stages of face perception.