Friday, October 7, 2016

Speech recognition

With the fast evolution of intelligent personal assistants like Siri and google now ,it's important to know how programs are now capable of understanding what we tell them. 

Speech recognition vs voice recognition 

Speech recognition is the ability of a machine or program to identify words and phrases in spoken language and convert them to a machine-readable format. 
The terms "speech recognition" and "voice recognition" are sometimes used interchangeably. However, the two terms mean different things. Speech recognition is used to identify words in spoken language. Voice recognition is a biometric technology used to identify a particular individual's voice.

How does it work ?


Speech recognition is one of the most complex areas of computer science—and partly because it's interdisciplinary: it involves a mixture of extremely complex linguistics, mathematics, and computing itself
Broadly speaking, there are four different approaches a computer can take if it wants to turn spoken sounds into written words:
  1. Simple pattern matching (where each spoken word is recognized in its entirety—the way you instantly recognize a tree or a table without consciously analyzing what you're looking at)(It's like the scanner in java )
  2. Pattern and feature analysis (where each word is broken into bits and recognized from key features, such as the vowels it contains)(It's like how we use the arrays)
  3. Language modeling and statistical analysis (in which a knowledge of grammar and the probability of certain words or sounds following on from one another is used to speed up recognition and improve accuracy)
  4. Artificial neural networks (brain-like computer models that can reliably recognize patterns, such as word sounds, after exhaustive training)

Why is it so important ?

Because it's making our lives so much easier because now you can just ask your personal assistant on your phone or laptop to look up a meaning or play a song or even do a complex mathematical equation which spares us some time and effort, and trust me you're going to  want to chat with your personal assistant because nowadays they can be sassy, funny,and nice.


References:
1-http://www.and-bmod.com/wp-content/uploads/2015/01/Windows-Speech-Recognition-2-Featured.jpg
2-http://copia.com.au/wp-content/themes/copia/images/medicalspeech.png



1 comment:

  1. Very nice post. I liked how you connected it to the concepts we learned in class. I remember, for instance, the automatic captioning on YouTube being pretty bad at start. Now, I've seen videos where it works perfectly. It's progressed leaps and bounds and not only will the improvement of recognizing speech be an important change in the future, but program's abilities to parse complex statements like the example you gave at the end.

    ReplyDelete