Google Blogoscoped

Monday, December 17, 2007

Google Built Phone Service to Train Speech-to-Text Software

Funny. Google’s Marissa Mayer gave an interview to in October – spotted by Ionut – and mentioned how one of their services was built not necessarily to be profitable in itself... but to gather more data from us, the monkeys borg drones humans. Quote Marissa:

You may have heard about our [directory assistance] 1-800-GOOG-411 service.

(From the service’s help entry: “Call 1-800-GOOG-411. ... Say where you are and what you’re looking for. GOOG-411 will connect you with the business you choose.”)

Whether or not free-411 is a profitable business unto itself is yet to be seen. I myself am somewhat skeptical. The reason we really did it is because we need to build a great speech-to-text model ... that we can use for all kinds of different things, including video search.

The speech recognition experts that we have say: If you want us to build a really robust speech model, we need a lot of phonemes, which is a syllable as spoken by a particular voice with a particular intonation. So we need a lot of people talking, saying things so that we can ultimately train off of that. ... So 1-800-GOOG-411 is about that: Getting a bunch of different speech samples so that when you call up or we’re trying to get the voice out of video, we can do it with high accuracy.


Blog  |  Forum     more >> Archive | Feed | Google's blogs | About


This site unofficially covers Google™ and more with some rights reserved. Join our forum!