Apple SiriProxy: Mainstreaming Speech Recognition through Hobbyists

Hobbyists are using SiriProxy to push the boundaries of Apple Siri. Check this video out.

Futurists have been predicting we’ll be controlling our computers and electronics with speech for decades now. Will Apple Siri at long last bring it to fruition? Maybe.

Of course, engineers have been working on speech recogntion for a long time. My first exposure to it was a demonstration of Shoebox, a calculator with speech input, at the IBM pavillion at the 1964 World Fair. Yet despite years of research and hacking speech recognition remains a niche technology. This is why Apple Siri  and the SiriProxy tool, in particular, are so important.

Tools like SiriProxy allow hobbyists to push the tech forward. Check out this video of a hobbyist who configured Siri with SiriProxy to control the lights and other home electronics.

Apple Siri has a lot of infrastructure support that earlier speech recognition systems lacked. It sends the speech back to a server for recognition and that server has assimilated clues from massive amounts of data on speech patterns.

Once recognized, it relies on other services for search and to look for answers to questions. If you ask how far it is from Los Angeles to New York, it will call WolframAlpha for the answer. Ask it where to get Indian food in your neighborhood and it will call Yelp.

Google Voice also has access to a large speech sample database, too, but it’s playing catch up with answer retrieval. Conversely, Apple Siri is attracting a huge hobbyist following. This might be the key to the eventual mainstreaming of the tech. >

The developer of that app had to jump through hoops using SiriProxy to get it to work. Here’s hoping Apple views Siri as a platform and encourages this sort of thing.