Google Voice Search

If you are sick of typing search queries, there is a good news for you. Google has added voice search to its search home screen on Chrome browser. Although it was announced a few weeks back, I noticed it for the first time early this morning.

Look for the little microphone icon to the right of the search box on Google.com. The voice search feature works only with Google Chrome (version 11) because it is the first iteration that leverages the Chrome Speech API. Google Speech Technology manager Mike Cohen said at the Inside Search event that he and his team have logged 230 billion words to help Google’s English Voice Search system recognize common phrases. That is an incredible number. But all of those words won’t necessarily translate to accurate searches, because a lot depends on how Google’s algorithms handle the words when they’re paired together with other words.

I tested the new voice search feature of Google using a variety of searches and found it easy, fast, and accurate for about 50% of the voice searches. The diffrence is accuracy of the voice search might be due to the accent in which we Indians speak English and the way Americans do however it is a great feature. There is no doubt that Google Voice Search works better for american accents. All voice-recognition systems or programs make errors. There is also a problem with words that sound alike but are spelled differently and have different meanings - for example, "hear" and "here." With the launch of voice search, Google becomes the first search engine to successfully implement and release a ’speak to search’ feature.

How Google Voice Search Works?

The voice search feature on Google uses voice recognition technology so that users can search based on voice generated queries. A small microphone at the end of the search box can be clicked, which then captures voice entry. After a rapid processing cycle, the voice is converted to text and the search is executed.

What is Voice Recognition (Speech Recognition)?

According to TechTarget’s definition, Voice or speech recognition is the ability of a machine or program to receive and interpret dictation, or to understand and carry out spoken commands. For use with computers, analog audio must be converted into digital signals. This requires analog-to-digital conversion. For a computer to decipher the signal, it must have a digital database, or vocabulary, of words or syllables, and a speedy means of comparing this data with signals. The speech patterns are stored on the hard drive and loaded into memory when the program is run. A comparator checks these stored patterns against the output of the Analog-to-Digital converter. Google has used the same technology to power their voice search feature.

Voice Search Competition

Google may have some competition when it comes to voice activated searches. Apple is in the progress of acquiring a voice activated program that works in a similar format. Siri is a voice activated search engine will be offered on mobile phones. Apparently it was developed by the Pentagon and funded by the CIA. If Apple ever gets the system to run on an iPhone, Google just might be in trouble.