Medigy: Sound and Speech Recognition

Gaming will play an important role in the metaverse, and adding voice to games has long been a goal of game developers. The game flow is more natural with integrated voice controls. Gamers can use their voices to control in-game action and characters. Voice controls can be more intuitive, which reduces the learning curve for new users.

However, developing games is already a massive and costly undertaking. Adding voice controls that work well for global audiences adds to the complexity, and voice is still not widely used in video games. However, advances in speech technology enabled by AI make adding voice elements to games easier than ever before. Facebook/Meta, for example, is improving the speech recognition capabilities of its Oculus virtual reality headsets. More in-game voice elements, as well as voice-based games in the metaverse, are on the horizon.

Speech recognition systems must become far more efficient in order to run on-device on ultralight, compact, and fashionable glasses. And they will need to be much more accurate and robust — capable of disambiguating words and understanding context in the same way that humans do, capable of handling a large vocabulary and uncommon words, and capable of working well even in difficult situations with a lot of background noise and multiple people speaking.