Tim O'Reilly on Google 411 Service

by Bruce Stewart

Tim has posted an interesting theory about Google's recently announced 411 service over on the Radar blog. Is Google using the new service to build its own speech database?

But it also seems to me that there's a hidden story here about the speech recognition itself. I was talking recently to Eckart Walther of Yahoo!, who used to be at Tellme, and he pointed out that speech recognition took a huge leap in capability when automated speech recognition started being used for directory assistance. All of a sudden, there were millions of voices, millions of accents to train speech recognition systems on, and much less need for the individual user to train the system.

This is reminiscent of a comment that Peter Norvig, Director of Research at Google, made to me last year about automated translation, and why it's getting better. "We don't have better algorithms. We just have more data."

In short, I'm speculating that the 1-800-GOOG-411 service is designed to harvest voice data to build Google's own speech database, rather than licensing from Nuance or another player.

I don't have any inside knowledge, but I know just a little about how Google operates and this seem like a plausible theory to me.

With Tellme unveiling it's free mobile application for local business search today at the Web 2.0 Expo, this space looks like it's going to heat up in a hurry.