Skip to main content

Google Explains Secret to Its Siri Competitor

Google has explained the secret to the company's recently released update for its search app that added voice compatibility.

Ultimately, the quality of the app's service is based off a pool of data. Google said that the more data there is available, the better all web services will become. For better speech recognition, though, it means how that data is actually organized.

The company's voice search technology predominately utilizes data from anonymous queries on Google's search engine to receive the information it requires.

"The language model is the component of a speech recognizer that assigns a probability to the next word in a sentence given the previous ones," Google research scientist Ciprian Chelba said. "As an example, if the previous words are 'new york,' the model would assign a higher probability to 'pizza' than say 'granola.'"

Researching data for its voice search app led to Google scientists using up to 230 billion words from "a random sample of anonymized queries from Google.com that did not trigger spelling correction."

Chelba added that such a large batch of data can lead to word error rates being reduced by 6 to 10 percent. For systems that boast a wider range of operating points, meanwhile, Google said that word error reduction rates can be between 17 and 52 percent.

According to initial reaction, Google's Siri competitor delivers more solid results than Apple's own voice assistant. For example, in addition to delivering answers quicker than Siri, the app also shows voice transcriptions as queries are spoken by users; Siri only carries this out when a user is done talking.

 

Contact Us for News Tips, Corrections and Feedback

  • ivyanev
    Well the biggest difference for me is that it undurstands Bulgarian ;) , So it is not a race at all.
    Reply
  • freggo
    Now there is a clear home court advantage for Google of course as Apple simply does not have that kind of data pool available.
    That's gotta sting.

    Reply
  • This will force Apple to update the quality of Siri, so good news all around for all product users.
    Reply
  • archange
    Great job, Ciprian Chelba, keep up the good work!
    Reply
  • chibiwings
    In our country most of us are not english speaking natively but we have a neutral accent when speaking. but both software doesn't do any good when we used it..
    Reply
  • Ciprian Chelba is a romanian name. Romania rules with geeks :) ! Hai Romania
    Reply
  • thebigt42
    Does it kill the battery like Siri???
    Reply
  • SneakySnake
    thebigt42Does it kill the battery like Siri???
    Siri doesn't kill your battery. I use it a few dozens times a day, and my 4S gets the same battery life as my gf's who doesn't ever use Siri.
    Reply
  • makaveli316
    Am i the only one who think, that all those voice recognitions software are overhyped and useless?
    If we put aside people who want to look cool in front of other people by talking to the phone, who the hell use it? I can't imagine my self at home talking to the phone to do stuff for me.
    Maybe it's just me, but i prefer to tap twice and make a call.
    Plus i tried it few times and if your mother language isn't english, it is even more messy.
    Reply
  • jaquith
    For those with earlier iPhone's e.g. 4 it's the only option. Either works fine.
    Reply