Key points are not available for this paper at this time.
Depression is one of the most harmful diseases in society today, and the etiology and pathological mechanism of depression is one of the most complicated mental illnesses. As the population of people with depression grows, the patient's long duration of illness and the harmfulness of the results make the disease the biggest challenge in the diagnosis of mental illness. How to improve the recognition rate of depression and make diagnosis and treatment as early as possible is the most effective way. According to the clinical medical manifestations of patients with depression, it is found that there is a very obvious difference between the patients with depression and the normal group in terms of speech characteristics, such as lower tones and slower speech speed. Therefore, this paper proposes a method for intelligent recognition of depression based on speech signals in combination with the contemporary smart home environment. A novel ensemble support vector machine (ESVM) algorithm is proposed in this article, which is applied to several classic depression speech data sets. The organic combination of depression recognition and smart home environment can adapt to the development of future technology.
Zhang et al. (Fri,) studied this question.