Phoneme Approach For Text-to-Speech in SCIAM

jscribner writes "Scientific American is running a feature on IBM Research's Text-to-Speech technology. It discusses the current state of affairs in this field, and describes IBM's phoneme based 'Supervoices' approach. The IBM site provides a demonstration, allowing users to enter text to be rendered to speech, as well as providing several examples in other languages."

Comments

As a concerned American patriot,

[American-Patr10t]

I am ashamed that the president of the United States is from Texas. I sure didn't elect that cowboy!

And before anybody thinks this is offtopic, consider this: the Texan cowboy can't spell either (or at least, he can't count...)

Re:As a concerned American patriot,

[American-Patr10t]

Yes, they should be called Freedomgnomes.

Why? Are they called Frenchgnomes right now?

And where's freedomdot?

It's Slashdot, not Frenchdot.

I tells ya, it's all freedomin' wrong!

Now I understand. Freedom is not supposed to replace French. Now, do you want some f*ing fries with your bloody steak?

Freedom. The new Marklar.

Cocorico!

Re:As a concerned Slashdot reader..

[shepd]

>I find your posts, though insightful, tend to divert attention from the topic at the top of the thread.

Give this man a cookie!

Finally, someone who put it all together! And it only took 2640 posts for it to be noticed! Woohoo! (I hope you didn't read them all!).

(You'll notice I tend to deviate from topics on other forums as well. It's fun! But I always try to stay somewhat on topic, or at least on topic to the parent post. :-)

I'll try your suggestion some time, we'll see what happens.