Voice recognition works by matching the voice pattern of an individual person rather than by memorizing specific words. The computer compares your unique vocal sound patterns to its stored vocabulary, and it looks for the best match between the two.
What Is Voice Recognition?
Voice recognition is a set of algorithms that the assistants use to convert your speech into a digital signal and ascertain what you're saying. Programs like Microsoft Word use voice recognition to help type down words.
When was voice recognition invented?
The first voice recognition system was called the Audrey system. The name was a contraction of "Automated Digit Recognition." Invented in 1952 by Bell Laboratories, Audrey was able to recognize numerical digits. The speaker would say a number, and Audrey would light up one of 10 corresponding lightbulbs.
Why is voice recognition more accurate?
Because of this, when the voice recognition system identifies a phoneme, it uses the accrued data to predict which one will likely come next. Because RNNs continuously learn , the more it's used, the more accurate the voice recognition will be.
Why do we need filters on voice recognition?
For some voice recognition systems, frequencies that are higher and lower than the human's hearing range are filtered out.
How many phonemes are there in the English language?
There are around 40 phonemes in the English language. When the voice recognition system identifies one, it determines the probability of what the next one will be.
Creating voice assistant for games (tutorial for FIFA)
Enabling the “rainbow flick” skill in the game by giving voice command “flick right”.
Motivation: Why I chose FIFA?
If you have been playing FIFA through the years like me, you would know about the different key combinations you need to remember in order to change the tactics in the game.
Tutorial
For this tutorial, I’ll show how we can create a custom wake-word (like “Alexa” or “Okay Google”) and then fire a command to perform a skill move in the game.
Motivation: Why I Chose FIFA?
How Do Speech Recognition Algorithms Work?
- Assume we want to detect the wake-word “Okay EA”. We capture the raw audio from the microphone and convert it to a visual representation of spectrum of different frequencies present in the sound, called a spectrogram. This is inspired by how a human’s ear captures audio. Next, we feed thin slices of this spectrogram to a Recurrent Neural Network mo...
Tutorial
- For this tutorial, I’ll show how we can create a custom wake-word (like “Alexa” or “Okay Google”) and then fire a command to perform a skill move in the game.
Results
- Changing tactics during game:
More such results can be found on my YouTube channel, with the video embedded below. - Conclusion
It would be great if EA could incorporate such a voice assistant in the future editions of FIFA. It could become possible to give commands like “Substitute Pedro for Willian” or “Change formation to 4–4–2”and immediately see the changes in the game, without having to go to the pause men…