A weblog by Will Fitzgerald

Superhuman speech recognition?

Well, I got excited when I saw this article referenced on Slashdot: IBM Strives For “Superhuman” Speech Tech. It may be very good–and the Voicebox in-car technology looks similar to what we worked on at I/NET–but:

On their automatic translation software: “The software development kit (SDK) is available now, but no final products exist yet for consumers to purchase. A product will probably not be available to consumers for at least another 6 months, an IBM representative said.”

On their sort-of near real-time Arabic transcriber: “Don’t expect to tune it in during lunchtime, however; Roukos hinted that the price will to be in the hundreds of thousands of dollars.”

It turned out to be just a successful press release after all.


One response to “Superhuman speech recognition?

  1. Michael Hannemann January 25, 2006 at 4:07 pm

    I didn’t think it sounded “super-human” at all, but I did think it could be interesting. The interesting-ness depends on what exactly is going in the following quote:

    “Algorithms exist that can determine this context on the fly, so you don’t have to use predetermined sentence structure,” Kennewick explained. “[It’s accomplished by] tying speech content to some contextual cues by using environmental information,” such as a particular song playing on the XM receiver, he said.

%d bloggers like this: