Project Details
Description
Mental health problems and especially schizophrenia worldwide have increased considerably in recent decades.
This disorder is characterized by a distortion of perceptions, emotions, language, and self-awareness.
The language of these people usually has normal articulation and grammatical construction, however, some acoustic parameters of speech may be affected due to difficulty expressing emotions.
For their part, professionals in psychiatry and speech therapy have few options to treat these people due to the few technologies available.
Treatment for the expression of emotions must consider not only the processing of language and emotions but also the acoustic structure of the language and the physical changes that the expression of different emotions exerts on it.
This means that the changes we make to acoustic parameters such as volume, tone and speed of speech are essential for the proper use of language and the expression of emotions.
The estimation of acoustic parameters of the speech signal is a solved task that generates a large amount of data.
However, the correlation of these data with the expression of emotions is a complex, abstract task that requires a lot of training.
Since artificial intelligence offers great advantages in automatically extracting features and training robust models to recognize patterns that can classify different conditions, then why not train an artificial intelligence system so that it can recognize emotions in the Are you talking about people with schizophrenia?
This work proposes to create a system based on artificial intelligence that, after training with speech databases with different emotions, performs automatic recognition, but in speech signals from people with schizophrenia.
This disorder is characterized by a distortion of perceptions, emotions, language, and self-awareness.
The language of these people usually has normal articulation and grammatical construction, however, some acoustic parameters of speech may be affected due to difficulty expressing emotions.
For their part, professionals in psychiatry and speech therapy have few options to treat these people due to the few technologies available.
Treatment for the expression of emotions must consider not only the processing of language and emotions but also the acoustic structure of the language and the physical changes that the expression of different emotions exerts on it.
This means that the changes we make to acoustic parameters such as volume, tone and speed of speech are essential for the proper use of language and the expression of emotions.
The estimation of acoustic parameters of the speech signal is a solved task that generates a large amount of data.
However, the correlation of these data with the expression of emotions is a complex, abstract task that requires a lot of training.
Since artificial intelligence offers great advantages in automatically extracting features and training robust models to recognize patterns that can classify different conditions, then why not train an artificial intelligence system so that it can recognize emotions in the Are you talking about people with schizophrenia?
This work proposes to create a system based on artificial intelligence that, after training with speech databases with different emotions, performs automatic recognition, but in speech signals from people with schizophrenia.
Keywords
Schizophrenia, Rehabilitation, Acoustic analysis, Artificial intelligence.
Commitments / Obligations
A research article submitted or published in a national or international indexed journal Q<=3
Research training for an assistant (a graduated Biomedical Engineer) Dissemination through program seedbeds.
Research training for an assistant (a graduated Biomedical Engineer) Dissemination through program seedbeds.
| Status | Finished |
|---|---|
| Effective start/end date | 8/17/21 → 8/17/22 |
UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):
Main Funding Source
- Installed Capacity (Academic Unit)
Location
- Bogotá D.C.
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.