BİLDİRİLER

BİLDİRİ DETAY

Volkan OBAN, Gül DİKEÇ
ARTIFICIAL INTELLIGENCE APPLICATIONS IN HEALTHCARE: THE USE CASE –TEXT TO SPEECH IN PSYCHIATRY AREA
 
Last 20 years, writing about trauma or stressful events were widely used in clinical and non-clinical psychiatric field. Because writing has immediate and long-term physical and emotional benefits for human. Some studies were found writing was effective on mood, psychosocial well-being, post-traumatic intrusion and avoidance symptoms. It could provide emotional catharsis, less physiological stress and repeated exposure. Sometimes patients were not aware of their feeling and they could realize while they were writing. On the other hand, writing the stressful events is easier than talking with the others. Patients feels more comfortable themselves than without talking. Keep a diary or writing factors that increased and decreased emotions is important for conscious. Writing also provide personal awareness for their emotions and their life. Patients could read several times the texts that were written before and it helps to improve their mental health. Writing is often used to among people not only have anxiety disorders and mood disorders but also people without mental disorder. In today's digitalizing conditions, the health sector continues to gain positive momentum as machine learning and artificial intelligence (AI) develops and its applicability increases. AI can be defined as a method that computers can perform a number of tasks, often using human modeling, reasoning and problem-solving skills. The potential for the use of both AI and robotic technologies in the field of health is enormous. AI will improve healthcare decision support systems and enable healthcare professionals to make more accurate and efficient decisions with technology. One of the AI product is speech text. Speech text abbreviated as TTS (Text-to-Speech), is a type of speech synthesis that converts text into spoken audio output. Text for speech systems was first developed to assist visually impaired people by providing the user with a computer-generated spoken voice that can read text. gTTS (Google Text-to-Speech) text to speech in Python is a module and command line utility to save spoken text to mp3. It uses the Google Text to Speech (TTS) API. Google Cloud Text-to-Speech enables developers to synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants. It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks to deliver the highest fidelity possible. Depending on the patient's mood, the patient may want to express his / her feelings in writing rather than face to face and to listen to what you wrote over and over again. The patient may apply written language to express dominant feelings. At this point, one of the techniques used to communicate between the patient and the doctor will be the method in question. The aim of this presentation is to explain the benefits of TTS method which is planned to be applied to psychiatry.

Anahtar Kelimeler: Artificial Intelligence, Speech Recognition,Psychiatry,Text to Speech



 


Keywords: