As part of my GAM-401 'Intro to Games Futures' Module, I have been researching ways that industries have been improved by integrating game technology.
One of the industries I looked at was the healthcare industry, and specifically how speech synthesis technology is used to give people their voices back once they have lost them. Speech synthesis has been used in games for a very long time, originating with the early 80s Votrax Text to Speech Synthesizer which was used in arcade games such as Gorf.
This synthesizer could control its intonation and therefore create different sounds depending on what you wanted. It definitely still sounded VERY robotic, however.
Nowadays, speech synthesis has come a long way. I specifically stumbled across Voiceful, which can generate emotive human sounding speech:
Furthermore, I also discovered something called Overdub, which is a feature in Descript, a software used for writing scripts. It allows you to record voice overs or scripts that are read aloud by synthesised voices. It can even create a model of your own voice!
As well as this video, I was very impressed by the interactive demo on the Descript website, which shows just how accurate the synthetic voice can sound. The demo allows you to change a sentence by typing something in for the synthesized voice to overdub. I had a lot of fun with it! Try it out for yourself here!
Finally I discovered VocaliD, a service that allows people to generate their own synthesized voice for their assistive devices to use. This means people can have a direct representative of their own voice to use if they ever lose their voice due to a medical issue or otherwise. You can learn all about VocaliD and the services they offer at their website here.
Comentarios