Estimating Depressive Symptom Class from Voice.

Voice-based depression detection methods have been studied worldwide as an objective and easy method to detect depression. Conventional studies estimate the presence or severity of depression. However, an estimation of symptoms is a necessary technique not only to treat depression, but also to relieve patients' distress. Hence, we studied a method for clustering symptoms from HAM-D scores of depressed patients and by estimating patients in different symptom groups based on acoustic features of their speech. We could separate different symptom groups with an accuracy of 79%. The results suggest that voice from speech can estimate the symptoms associated with depression.

Detection of Major Depressive Disorder Based on a Combination of Voice Features: An Exploratory Approach.

In general, it is common knowledge that people's feelings are reflected in their voice and facial expressions. This research work focuses on developing techniques for diagnosing depression based on acoustic properties of the voice. In this study, we developed a composite index of vocal acoustic properties that can be used for depression detection. Voice recordings were collected from patients undergoing outpatient treatment for major depressive disorder at a hospital or clinic following a physician's diagnosis. Numerous features were extracted from the collected audio data using openSMILE software. Furthermore, qualitatively similar features were combined using principal component analysis. The resulting components were incorporated as parameters in a logistic regression based classifier, which achieved a diagnostic accuracy of ~90% on the training set and ~80% on the test set. Lastly, the proposed metric could serve as a new measure for evaluation of major depressive disorder.

Evaluation of emotional arousal level and depression severity using voice-derived sound pressure change acceleration.

In this research, we propose a new index of emotional arousal level using sound pressure change acceleration, called the emotional arousal level voice index (EALVI), and investigate the relationship between this index and depression severity. First, EALVI values were calculated from various speech recordings in the interactive emotional dyadic motion capture database, and the correlation with the emotional arousal level of each voice was examined. The resulting correlation coefficient was 0.52 (n = 10,039, p < 2.2 × 10-16). We collected a total of 178 datasets comprising 10 speech phrases and the Hamilton Rating Scale for Depression (HAM-D) score of outpatients with major depression at the Ginza Taimei Clinic (GTC) and the National Defense Medical College (NDMC) Hospital. The correlation coefficients between the EALVI and HAM-D scores were - 0.33 (n = 88, p = 1.8 × 10-3) and - 0.43 (n = 90, p = 2.2 × 10-5) at the GTC and NDMC, respectively. Next, the dataset was divided into "no depression" (HAM-D < 8) and "depression" groups (HAM-D ≥ 8) according to the HAM-D score. The number of patients in the "no depression" and "depression" groups were 10 and 78 in the GTC data, and 65 and 25 in the NDMC data, respectively. There was a significant difference in the mean EALVI values between the two groups in both the GTC and NDMC data (p = 8.9 × 10-3, Cliff's delta = 0.51 and p = 1.6 × 10-3; Cliff's delta = 0.43, respectively). The area under the curve of the receiver operating characteristic curve when discriminating both groups by EALVI was 0.76 in GTC data and 0.72 in NDMC data. Indirectly, the data suggest that there is some relationship between emotional arousal level and depression severity.

Depressive Mood Assessment Method Based on Emotion Level Derived from Voice: Comparison of Voice Features of Individuals with Major Depressive Disorders and Healthy Controls.

BACKGROUND: In many developed countries, mood disorders have become problematic, and the economic loss due to treatment costs and interference with work is immeasurable. Therefore, a simple technique to determine individuals' depressive state and stress level is desired. METHODS: We developed a method to assess specific the psychological issues of individuals with major depressive disorders using emotional components contained in their voice. We propose two indices: vitality, a short-term index, and mental activity, a long-term index capturing trends in vitality. To evaluate our method, we used the voices of healthy individuals (n = 14) and patients with major depression (n = 30). The patients were also assessed by specialists using the Hamilton Rating Scale for Depression (HAM-D). RESULTS: A significant negative correlation existed between the vitality extracted from the voices and HAM-D scores (r = -0.33, p < 0.05). Furthermore, we could discriminate the voice data of healthy individuals and patients with depression with a high accuracy using the vitality indicator (p = 0.0085, area under the curve of the receiver operating characteristic curve = 0.76).

Performance Evaluation of a Voice-Based Depression Assessment System Considering the Number and Type of Input Utterances.

It is empirically known that mood changes affect facial expressions and voices. In this study, the authors have focused on the voice to develop a method for estimating depression in individuals from their voices. A short input voice is ideal for applying the proposed method to a wide range of applications. Therefore, we evaluated this method using multiple input utterances while assuming a unit utterance input. The experimental results revealed that depressive states could be estimated with sufficient accuracy using the smallest number of utterances when positive utterances were included in three to four input utterances.

Evaluation of the Severity of Major Depression Using a Voice Index for Emotional Arousal.

Recently, the relationship between emotional arousal and depression has been studied. Focusing on this relationship, we first developed an arousal level voice index (ALVI) to measure arousal levels using the Interactive Emotional Dyadic Motion Capture database. Then, we calculated ALVI from the voices of depressed patients from two hospitals (Ginza Taimei Clinic (H1) and National Defense Medical College hospital (H2)) and compared them with the severity of depression as measured by the Hamilton Rating Scale for Depression (HAM-D). Depending on the HAM-D score, the datasets were classified into a no depression (HAM-D < 8) and a depression group (HAM-D ≥ 8) for each hospital. A comparison of the mean ALVI between the groups was performed using the Wilcoxon rank-sum test and a significant difference at the level of 10% (p = 0.094) at H1 and 1% (p = 0.0038) at H2 was determined. The area under the curve (AUC) of the receiver operating characteristic was 0.66 when categorizing between the two groups for H1, and the AUC for H2 was 0.70. The relationship between arousal level and depression severity was indirectly suggested via the ALVI.

Effectiveness of a Voice-Based Mental Health Evaluation System for Mobile Devices: Prospective Study.

BACKGROUND: We developed a system for monitoring mental health using voice data from daily phone calls, termed Mind Monitoring System (MIMOSYS), by implementing a method for estimating mental health status from voice data. OBJECTIVE: The objective of this study was to evaluate the potential of this system for detecting depressive states and monitoring stress-induced mental changes. METHODS: We opened our system to the public in the form of a prospective study in which data were collected over 2 years from a large, unspecified sample of users. We used these data to analyze the relationships between the rate of continued use, the men-to-women ratio, and existing psychological tests for this system over the study duration. Moreover, we analyzed changes in mental data over time under stress from particular life events. RESULTS: The system had a high rate of continued use. Voice indicators showed that women have more depressive tendencies than men, matching the rate of depression in Japan. The system's voice indicators and the scores on classical psychological tests were correlated. We confirmed deteriorating mental health for users in areas affected by major earthquakes in Japan around the time of the earthquakes. CONCLUSIONS: The results suggest that although this system is insufficient for detecting depression, it may be effective for monitoring changes in mental health due to stress. The greatest feature of our system is mental health monitoring, which is most effectively accomplished by performing long-term time-series analysis of the acquired data considering the user's life events. Such a system can improve the implementation of patient interventions by evaluating objective data along with life events.

A new method of Bayesian causal inference in non-stationary environments.

Bayesian inference is the process of narrowing down the hypotheses (causes) to the one that best explains the observational data (effects). To accurately estimate a cause, a considerable amount of data is required to be observed for as long as possible. However, the object of inference is not always constant. In this case, a method such as exponential moving average (EMA) with a discounting rate is used to improve the ability to respond to a sudden change; it is also necessary to increase the discounting rate. That is, a trade-off is established in which the followability is improved by increasing the discounting rate, but the accuracy is reduced. Here, we propose an extended Bayesian inference (EBI), wherein human-like causal inference is incorporated. We show that both the learning and forgetting effects are introduced into Bayesian inference by incorporating the causal inference. We evaluate the estimation performance of the EBI through the learning task of a dynamically changing Gaussian mixture model. In the evaluation, the EBI performance is compared with those of the EMA and a sequential discounting expectation-maximization algorithm. The EBI was shown to modify the trade-off observed in the EMA.

Extended Bayesian inference incorporating symmetry bias.

We start by proposing a causal induction model that incorporates symmetry bias. This model has two parameters that control the strength of symmetry bias and includes conditional probability and conventional models of causal induction as special cases. We calculated the determination coefficients between assessments by participants in eight types of causal induction experiments and the estimated values using the proposed model. The mean coefficient of determination was 0.93. Thus, it can reproduce causal induction of human judgment with high accuracy. We further propose a human-like Bayesian inference method to replace the conditional probability in Bayesian inference with the aforementioned causal induction model. In this method, two components coexist: the component of Bayesian inference, which updates the degree of confidence for each hypothesis, and the component of inverse Bayesian inference that modifies the model of each hypothesis. In other words, this method allows not only inference but also simultaneous learning. Our study demonstrates that the method addresses unsteady situations where the target of inference occasionally changes not only by making inferences based on knowledge (model) and observation data, but also by modifying the model itself.

Mental status assessment of disaster relief personnel by vocal affect display based on voice emotion recognition.

BACKGROUND: Disaster relief personnel tend to be exposed to excessive stress, which can be a cause of mental disorders. To prevent from mental disorders, frequent assessment of mental status is important. This pilot study aimed to examine feasibility of stress assessment using vocal affect display (VAD) indices as calculated by our proposed algorithms in a situation of comparison between different durations of stay in stricken area as disaster relief operation, which is an environment highly likely to induce stress. METHODS: We used Sensibility Technology (ST) software to analyze VAD from voices of participants exposed to extreme stress for either long or short durations, and we proposed algorithms for indices of low VAD (VAD-L), high VAD (VAD-H), and VAD ratio (VAD-R), calculated from the intensity of emotions as measured by voice emotion analysis. As a preliminary validation, 12 members of Japan Self-Defense Forces dispatched overseas for long (3 months or more) or short (about a week) durations were asked to record their voices saying 11 phrases repeatedly across 6 days during their dispatch. RESULTS: In the validation, the two groups showed an inverse relationship in VAD-L and VAD-H, in that long durations in disaster zones resulted in higher values of both VAD-L and VAD-R, and lower values of VAD-H, compared with short durations. Interestingly, phrases produced varied results in terms of group differences and VAD indices, demonstrating the sensitivity of the ST. CONCLUSIONS: A comparison of the values obtained for the different groups of subjects clarified that there were tendencies of the VAD-L, VAD-H, and VAD-R indices observed for each group of participants. The results suggest the possibility of using ST software in the measurement of affective aspects related to mental health from vocal behavior.