Andrea Guidi

Speech analysis for mood state characterization in bipolar patients

Bipolar disorders are characterized by an unpredictable behavior, resulting in depressive, hypomanic or manic episodes alternating with euthymic states. A multi-parametric approach can be followed to estimate mood states by integrating information coming from different physiological signals and from the analysis of voice. In this work we propose an algorithm to estimate speech features from running speech with the aim of characterizing the mood state in bipolar patients. This algorithm is based on an automatic segmentation of speech signals to detect voiced segments, and on a spectral matching approach to estimate pitch and pitch changes. In particular average pitch, jitter and pitch standard deviation within each voiced segment, are estimated. The performances of the algorithm are evaluated on a speech database, which includes an electroglottographic signal. A preliminary analysis on subjects affected by bipolar disorders is performed and results are discussed.

A synergy-based hand control is encoded in human motor cortical areas

How the human brain controls hand movements to carry out different tasks is still debated. The concept of synergy has been proposed to indicate functional modules that may simplify the control of hand postures by simultaneously recruiting sets of muscles and joints. However, whether and to what extent synergic hand postures are encoded as such at a cortical level remains unknown. Here, we combined kinematic, electromyography, and brain activity measures obtained by functional magnetic resonance imaging while subjects performed a variety of movements towards virtual objects. Hand postural information, encoded through kinematic synergies, were represented in cortical areas devoted to hand motor control and successfully discriminated individual grasping movements, significantly outperforming alternative somatotopic or muscle-based models. Importantly, hand postural synergies were predicted by neural activation patterns within primary motor cortex. These findings support a novel cortical organization for hand movement control and open potential applications for brain-computer interfaces and neuroprostheses. DOI: http://dx.doi.org/10.7554/eLife.13420.001

A Novel Algorithm for Movement Artifact Removal in ECG Signals Acquired from Wearable Systems Applied to Horses

This study reports on a novel method to detect and reduce the contribution of movement artifact (MA) in electrocardiogram (ECG) recordings gathered from horses in free movement conditions. We propose a model that integrates cardiovascular and movement information to estimate the MA contribution. Specifically, ECG and physical activity are continuously acquired from seven horses through a wearable system. Such a system employs completely integrated textile electrodes to monitor ECG and is also equipped with a triaxial accelerometer for movement monitoring. In the literature, the most used technique to remove movement artifacts, when noise bandwidth overlaps the primary source bandwidth, is the adaptive filter. In this study we propose a new algorithm, hereinafter called Stationary Wavelet Movement Artifact Reduction (SWMAR), where the Stationary Wavelet Transform (SWT) decomposition algorithm is employed to identify and remove movement artifacts from ECG signals in horses. A comparative analysis with the Normalized Least Mean Square Adaptive Filter technique (NLMSAF) is performed as well. Results achieved on seven hours of recordings showed a reduction greater than 40% of MA percentage (between before- and after- the application of the proposed algorithm). Moreover, the comparative analysis with the NLMSAF, applied to the same ECG recordings, showed a greater reduction of MA percentage in favour of SWMAR with a statistical significant difference (p–value < 0.0.5).

Smartphone Application for the Analysis of Prosodic Features in Running Speech with a Focus on Bipolar Disorders: System Performance Evaluation and Case Study

Bipolar disorder is one of the most common mood disorders characterized by large and invalidating mood swings. Several projects focus on the development of decision support systems that monitor and advise patients, as well as clinicians. Voice monitoring and speech signal analysis can be exploited to reach this goal. In this study, an Android application was designed for analyzing running speech using a smartphone device. The application can record audio samples and estimate speech fundamental frequency, F0, and its changes. F0-related features are estimated locally on the smartphone, with some advantages with respect to remote processing approaches in terms of privacy protection and reduced upload costs. The raw features can be sent to a central server and further processed. The quality of the audio recordings, algorithm reliability and performance of the overall system were evaluated in terms of voiced segment detection and features estimation. The results demonstrate that mean F0 from each voiced segment can be reliably estimated, thus describing prosodic features across the speech sample. Instead, features related to F0 variability within each voiced segment performed poorly. A case study performed on a bipolar patient is presented.

Automatic analysis of speech F0 contour for the characterization of mood changes in bipolar patients

Abstract Bipolar disorders are characterized by a mood swing, ranging from mania to depression. A system that could monitor and eventually predict these changes would be useful to improve therapy and avoid dangerous events. Speech might convey relevant information about subjects’ mood and there is a growing interest to study its changes in presence of mood disorders. In this work we present an automatic method to characterize fundamental frequency (F0) dynamics in voiced part of syllables. The method performs a segmentation of voiced sounds from running speech samples and estimates two categories of features. The first category is borrowed from Taylors Tilt intonational model. However, the meaning of the proposed features is different from the meaning of Taylors ones since the former are estimated from all voiced segments without performing any analysis of intonation. A second category of features takes into account the speed of change of F0. In this work, the proposed features are first estimated from an emotional speech database. Then, an analysis on speech samples acquired from eleven psychiatric patients experiencing different mood states, and eighteen healthy control subjects is introduced. Subjects had to perform a text reading task and a picture commenting task. The results of the analysis on the emotional speech database indicate that the proposed features can discriminate between high and low arousal emotions. This was verified both at single subject and group level. An intra-subject analysis was performed on bipolar patients and it highlighted significant changes of the features with different mood states, although this was not observed for all the subjects. The directions of the changes estimated for different patients experiencing the same mood swing, were not coherent and were task-dependent. Interestingly, a single-subject analysis performed on healthy controls and on bipolar patients recorded twice with the same mood label, resulted in a very small number of significant differences. In particular a very good specificity was highlighted for the Taylor-inspired features and for a subset of the second category of features, thus strengthening the significance of the results obtained with patients. Even if the number of enrolled patients is small, this work suggests that the proposed features might give a relevant contribution to the demanding research field of speech-based mood classifiers. Moreover, the results here presented indicate that a model of speech changes in bipolar patients might be subject-specific and that a richer characterization of subject status could be necessary to explain the observed variability.

Removing movement artifacts from equine ECG recordings acquired with textile electrodes.

This study reports on the implementation of a novel system to detect and reduce movement artifact (MA) contribution in electrocardiogram (ECG) recordings acquired from horses in free movement conditions. The system comprises both integrated textile electrodes for ECG acquisition and one triaxial accelerometer for movement monitoring. Here, ECG and physical activity are continuously acquired from seven horses through the wearable system and a model that integrates cardiovascular and movement information to estimate the MA contribution is implemented. Moreover, in this study we propose a new algorithm where the Stationary Wavelet Transform (SWT) decomposition algorithm is employed to identify and remove movement artifacts from ECG recodigns. Achieved results showed a reduction of MA percentage greater than 40% between before- and after- the application of the proposed algorithm to seven hours of recordings.

Quantitative heartbeat coupling measures in human-horse interaction

We present a study focused on a quantitative estimation of a human-horse dynamic interaction. A set of measures based on magnitude and phase coupling between heartbeat dynamics of both humans and horses in three different conditions is reported: no interaction, visual/olfactory interaction and grooming. Specifically, Magnitude Squared Coherence (MSC), Mean Phase Coherence (MPC) and Dynamic Time Warping (DTW) have been used as estimators of the amount of coupling between human and horse through the analysis of their heart rate variability (HRV) time series in a group of eleven human subjects, and one horse. The rationale behind this study is that the interaction of two complex biological systems go towards a coupling process whose dynamical evolution is modulated by the kind and time duration of the interaction itself. We achieved a congruent and consistent statistical significant difference for all of the three indices. Moreover, a Nearest Mean Classifier was able to recognize the three classes of interaction with an accuracy greater than 70%. Although preliminary, these encouraging results allow a discrimination of three distinct phases in a real human-animal interaction opening to the characterization of the empirically proven relationship between human and horse.We present a study focused on a quantitative estimation of a human-horse dynamic interaction. A set of measures based on magnitude and phase coupling between heartbeat dynamics of both humans and horses in three different conditions is reported: no interaction, visual/olfactory interaction and grooming. Specifically, Magnitude Squared Coherence (MSC), Mean Phase Coherence (MPC) and Dynamic Time Warping (DTW) have been used as estimators of the amount of coupling between human and horse through the analysis of their heart rate variability (HRV) time series in a group of eleven human subjects, and one horse. The rationale behind this study is that the interaction of two complex biological systems go towards a coupling process whose dynamical evolution is modulated by the kind and time duration of the interaction itself. We achieved a congruent and consistent statistical significant difference for all of the three indices. Moreover, a Nearest Mean Classifier was able to recognize the three classes of interaction with an accuracy greater than 70%. Although preliminary, these encouraging results allow a discrimination of three distinct phases in a real human-animal interaction opening to the characterization of the empirically proven relationship between human and horse.

Features of vocal frequency contour and speech rhythm in bipolar disorder

Abstract Mental diseases are increasingly common. Among these, bipolar disorders heavily affect patients’ lives given the mood swings ranging from mania to depression. Voice has been shown to be an important cue to be investigated in relation with this kind of disease. In fact, several speech-related features have been used to characterize voice in depressed speakers. The goal is to develop a decision support system facilitating diagnosis and possibly predicting mood changes. Recently, efforts were devoted to studies concerning bipolar patients. A spectral analysis of F0-contours extracted from audio recordings of a text read by bipolar patients and healthy control subject is reported. The algorithm is automatic and the obtained features describe parsimoniously speech rhythm and intonation. Bipolar patients were recorded while experiencing different mood states, whereas the control subjects were recorded at different days. Feature trends are detected in bipolar patients across different mood states, while no significant differences are observed in healthy subjects.

The role of nonlinear coupling in Human-Horse Interaction: A preliminary study

This study focuses on the analysis of human-horse dynamic interaction using cardiovascular information exclusively. Specifically, the Information Theoretic Learning (ITL) approach has been applied to a Human-Horse Interaction paradigm, therefore accounting for the nonlinear information of the heart-heart interplay between humans and horses. Heartbeat dynamics was gathered from humans and horses during three experimental conditions: absence of interaction, visual-olfactory interaction, and brooming. Cross Information Potential, Cross Correntropy, and Correntropy Coefficient were computed to quantitatively estimate nonlinear coupling in a group of eleven subjects and one horse. Results showed a statistical significant difference on all of the three interaction phases. Furthermore, a Support Vector Machine classifier recognized the three conditions with an accuracy of 90:9%. These preliminary and encouraging results suggest that ITL analysis provides viable metrics for the quantitative evaluation of human-horse interaction.

Heart rate variability analysis during muscle fatigue due to prolonged isometric contraction

Fatigue can be defined as the muscular condition occurring before the inability to perform a task. It can be assessed through the evaluation of the median and mean frequency of the spectrum of the surface electromyography series. Previous studies investigated the relationship between heartbeat dynamics and muscular activity. However, exploitation of such cardiovascular measures to automatically identify muscle fatigue during fatiguing exercises is still missing. To this extent, HRV signals were gathered from 32 subjects during an isometric contraction task, and features defined in the time, frequency and nonlinear domains were investigated. We used surface electromyography to label the occurrence of muscle fatigue. Statistically significant differences were observed by comparing features related to fatigued subjects with the non-fatigued ones. Moreover, a pattern recognition system capable to achieve an average accuracy of 78.24% was implemented. These results confirmed the hypothesis that a relationship between heartbeat dynamics and muscle fatigue might exist.