Wednesday March 08, 2006 Emotional Speech Technology
|
I recently saw a couple of announcements for speech technology that now factors in emotions. |
On the Automatic Speech Recognition (ASR) side: yesterday's "What's New Now from Ziff Davis" email newsletter gave a pointer to an entry on the Gearlog blog for some mood flowers:
Each flower contains a microphone that captures voice data for emotional processing, the results of which are sent via wireless LAN to the counterpoint flower. Then, the embedded LEDs in the KOTOHANAs change color - yellow for happy, blue for sad, and so on - depending on what the person who's hanging on to the other one is feeling.
They're able to do this with an "emotion recognition engine" called Sensibility Technology (ST), developed by SGI Japan with the cooperation of AGI.
Sound's cool. I'm looking forward to it being a real product.
On the Text-to-Speech (TTS) side: there was an announcement last month to the Blind Linux Announce email alias for OpenMary, an Open Source Emotional Text-to-Speech Synthesis System.
MARY is a multi-lingual (German, English, Tibetan) and multi-platform (Windows, Linux, MacOs X and Solaris) speech synthesis system.
More details on Open Mary here.
I wonder what the market is like for open source emotional TTS's in Tibet?
[Technorati Tag: Speech Technology]
( Mar 08 2006, 10:34:32 AM PST ) [Listen] Permalink
Comments are closed for this entry.
![[ Registered ]](http://www.diarist.net/registry/button.gif ){kind=small}
