Is It a Unicorn?! Recognize Any Sound, Cross-Platform
Custom Multilingual Sound Recognition. Plus, a Voice Interface Without NLU
Let's clear one thing up: our keyword recognizer is actually a sound recognizer that runs across 5 platforms. For example, just 100 lines of Python is all that's needed to make an automated swear jar (no matter the language you swear in)! But as a sound recognizer, it can be trained to recognize any sound—your cat's meow, a guitar note. Since voice is sound, keyword recognition is multilingual and customizable. Read on for all the concepts, examples, how-to videos, and explainers you need to know to start using keyword recognition.
What's a Keyword Model, and Why Would I Use One?
Keyword recognition isn’t quite the household term that “ASR”, “NLU”, and “TTS” are. In this post, we’ll lay out what a keyword recognition model does, where it fits into the Spokestack speech processing model, and why you might (or might not) want to use one.
How to Create a Personal Keyword Model
Watch a 5-minute walk-through showing how to create and train your own custom, personal keyword recognizer.
A Swear Jar in 100 Lines of Python
The concept of a swear jar is simple: you have a list of words or short phrases that you’d like to stop saying, or stop someone else from saying. Every time one of those words does slip out, you drop a coin in a jar. If swearing’s not your thing, this concept also lets you reward yourself for saying nice things—call it a “compliment jar”. We wouldn’t want to limit this tutorial to us reprobates.