Technology Review - Published By MIT
Advertisement

The Search for Voice Activation

Continued from page 1

By Kate Greene

Friday, April 21, 2006

smaller text tool iconmedium text tool iconlarger text tool icon

Voice-activated systems, while getting better, can still sometimes get the answers wrong, explains Morgan. The software matches the voice input to a number of possibilities and often asks the user if the system's highest-ranked word was the one he or she intended, or it might say the word was unintelligible. These systems work best when the algorithm needs to access only a small dictionary, he adds, such as ring-tone options, movie listings, or phone-book contacts.

That methodology, though, would be impractical for Web searches, since it's impossible to limit the search dictionary while providing access to the eight billion-plus websites that Google searches.

Google's voice search patent approaches the problem by taking a step back from simply plugging standard voice-recognition technology into standard search technology, says Morgan. Instead of trying to accurately predict the single-best guess about what a person is saying, the technology would take a handful of word and phrase possibilities and throw them at the powerful Google search engine. In this way, the voice search system may not need the most accurate speech recognition technology. Instead, it relies on Google's strength -- its search algorithm -- to supply the most likely result for a number of possibilities.

This strategy of outsourcing the translation and searching to remote Google servers has its benefits, says Jordan Cohen, senior scientist at SRI International in Palo Alto, CA. It reduces the level of complexity in the software on the phone, and therefore wouldn't use as much processing power, memory, or energy. Instead, it relies on the strength of the network -- and some faith that the technology would be able to deal with the uncertainty of both vocal input and an intended search. If speech technology is instead confined to the mobile device, Cohen says, the software can "count on the person to fix things up" when the algorithm can't find the most suitable word.

Because mobile voice search has barely begun to take form, it remains an open question whether Google's approach will be employed -- or produce the best product. But the market for mobile search in general is "going to be immense," says Cohen. "The Google patent is an attempt to stake out a claim in that space."

Comments

  • Super Concept
    Certainly this could get big in terms of "Local Search" and maps based applications. Where people can query by voice about a particular thing they are looking for somewhere and they get back detailed instructions, description or whatever the information with power of Google search engine.

    http://www.Suchit-Tiwari.Org
    Rate this comment: 12345
    Guest (Suchit)
    04/21/2006
    Posts:1
    • Accent
      Both NOISE POLLUTION [New] LAWS and/or Lack of laws and Accents will be in the way
      However, I keenly await the day when I can use this life saving technology. Go Google!
      Rate this comment: 12345
      Guest (Bibi Kaur)
      04/21/2006
      Posts:1
  • Hurdles
    As anyone who has used voice activated phone system knows - this technology looks good but will be hard to implement. It has a frustration factor that will be hard to overcome. No one I know has the patience to parse the voice options to get to a result. Doing a search on a computer is different because you see a screenful of results from which you can pick quickly what you want or move on.
    Rate this comment: 12345
    Guest (Sastri)
    04/21/2006
    Posts:1
  • Download Voice Tools from Voice Web Solutions
    Speech activate web pages at VoiceWebSolutions.net
    Rate this comment: 12345
    Guest (Brian Ty Graham)
    04/21/2006
    Posts:1
  • Voice Activation
    Human Speach is a series of tones at given frequency and amplitudes.  Certain residual background noises emulate what sounds like conversation from a distance.  It is suprising how close sounding to speach noise sources can become.  As with anything it is how one acclimates to the tonal quality that brings understanding.  Think of a bus station loudspeaker system, no one can understand what is broadcast when first exposed.  After a bit of time, however, an individual will atune to the to the altered frequency and modulation and begin to discriminate words.  Look further at how humans adapt to learn understand what machines must do to achieve learning.
    Rate this comment: 12345
    Guest (Bewulf)
    04/28/2006
    Posts:1

Log In

Forgot your password?     Register »
Advertisement

Videos

Prescription: Networking
Technology Review November/December 2009

Current Issue

Natural Gas Changes the Energy Map
The United States has vast supplies of this cleaner fossil fuel. But how should we use it?
Featured Content
Sponsored by:
White Papers

Twelve ways to reduce costs with SQL Server 2008
Find out how to reduce costs and get more efficient

Download

Total Economic Impact of SQL Server 2008 Upgrade
Forrester reports on increasing productivity and management capabilities

Download 

Achieving Cost and Resource Savings with UC
How Office Communications Server R2 and Exchange Server can make your business smarter and more efficient

Download 
Advertisement
Subscribe to Technology Review's daily e-mail update. Enter your e-mail address

TECHNOLOGY RESOURCES
Advertisement
MIT Massachusetts Institute of Technology © 2009 Technology Review. All Rights Reserved.