5 Simulations That Need Emotive Synthetic Speech

Euphony
Euphony
Apr 19, 2017 · 4 min read

Virtual reality is more than a game. Simulation training (or virtual reality training) is a reliable method of training for thousands of professionals. From the airline industry to skilled trades, simulation training provides a virtual medium through which a wide range of skills can be learned.

Many simulations are driven by language technology. This allows users to speak to the simulation and receive an audible response. The current state of the art solution is to record voice actors speaking in many different manners to work across different scenarios.

To the detriment of simulations, natural-sounding avatars have yet to substantially break into the industry. When simulations don’t use expensive voice actors, they may settle for robotic voices that distract from the simulation. Training environments can benefit from convincing, emotive synthetic speech, or text-to-speech that reflects emotion.

As industries and regulations change, companies are forced to adapt their training simulations. This means new scripts, which require companies to rehire expensive voice actors to reflect the changes. Emotive synthetic voice eliminates this problem. Text-to-speech allows organizations to quickly adapt their simulations.

Let’s look at five simulations that could benefit from emotive synthetic speech:

1. Air Traffic Controller and Pilot Training

Since 2008, simulator training for professionals in the airline industry has taken off. These simulators reduce dependency on operational on-the-job training. Students can experience high-risk, high-stress scenarios, without compromising safety. MITRE, a nonprofit that operates federally funded research and development centers, suggests that scenario-based instruction and voice recognition reduce the cost and time required to attain Certified Professional Controller status. Air traffic controller and pilot training are ideal candidates for synthetic text-to-speech. Air traffic controllers adjust their pitch and tone of voice as they issue instructions. Emotive synthetic speech would reflect this.

2. Combat and Law Enforcement Training

From improvised explosive device (IED) scenarios to live-shooter trainings, simulations provide valuable, risk-free learning opportunities for officers and combat teams. Trainees can learn from their mistakes in life or death scenarios. In Arizona, officers are trained using a 300-degree, 5-screen Multiple Interaction Learning Option system, or simulator. In one of the scenarios, a woman threatens to hurt a baby. Officers must interact with the woman and respond as the situation progresses. The outcome of the scenario is based on the deputy’s reaction. Synthetic text-to-speech would enable infinite scenarios and responses. Simulations could be altered to reflect current events and produce convincing human interactions.

3. Skilled Training

Skilled trades such as welding, are being supplemented with virtual reality. These simulations enhance welding training programs by reducing waste and scrap, providing tangible savings. They also enhance learning because they allow students to repeat a task as many times as necessary. These simulations could benefit from the integration of lifelike synthetic voice to imitate instructors and other welders. By increasing believability, simulations increase student engagement and heighten learning.

4. Therapy Sessions

Many people are immobilized by fear. Whether they’re afraid of heights, public speaking, or interviewing for a job, this fear can disrupt their life. Simulation training can help them work through their fears. A study was conducted to simulate job interviews for people with psychiatric disabilities.

According to the researchers, “Almost all [participants] described the interview as anxiety provoking, but the anxiety lessened as they became more skilled [through the simulation].” To improve the user experience, therapeutic simulations could benefit from lifelike synthetic voice. With cost-effective text-to-speech, questions could be changed to fit various industries and positions.

5. Architectural Walkthroughs

Virtual reality walkthroughs for construction projects — like this Chick-fil-A restaurant — are an effective way to experience a building before construction even starts. In the architectural world, designers often suggest various design options to their clients. In addition, changes are often made over the course of the build. Virtual reality architectural walkthroughs could benefit from descriptive voice-over explaining features and proposed changes. Emotive synthetic speech could enhance walkthroughs for clients.

Emotive synthetics voice is a cost-effective way to bring simulations to life. In many cases, emotive synthetic voice is a better alternative than hiring voice actors or using audio banks. It allows quick, cost-effective changes and the ability to overlay emotion on a voice. From training air traffic controllers to enhancing architectural walkthroughs, the application of synthetic text-to-speech is seemingly limitless.

Do you have an application for emotive synthetic speech? Let us know in the comments!


Euphony’s text-to-speech API generates authentic voice outputs with customizable emotions. It’s flexible, platform agnostic and well-documented. Learn more.


☞ If you enjoyed this please consider clicking or tapping the “︎❤”

    Euphony

    Written by

    Euphony

    A platform for generating authentic text-to-speech voices with emotional range.

    Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
    Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
    Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade