Embedded Webblog

Jun 11 2007 7:47PM | Permalink | Email this | Comments (0) |
Blog This! using:  Blogger.com | LiveJournal |
Digg This | Slashdot This | add to Del.icio.us

Although it has yet to find widespread application in the real world, the favorite user interface in most science fiction books and movies has been direct verbal interaction. A user simply tells the system what to do and the response is delivered verbally thereby eliminating costly mechanical inputs and data displays. Sensory, Inc. has recently updated their technology to ease the transition to the voice user interface for embedded devices. Their new RSC-4192O is a single chip product capable of speech recognition as well as compressed speech synthesis. To compliment the new IC, Sensory also released an enhanced version of its firmware to improve noise-immunity, speech and music synthesis, and multi-language speech recognition accuracy.  The new firmware, called FluentChip 3.0 also includes speaker dependent, speaker independent, and speaker verification speech recognition. In addition to a standard demonstration and evaluation toolkit for $199, Sensory also offers a voice recognition module in a 40-pin DIP footprint to ease the integration into breadboard products. The module features data EEPROM plus audio I/O to allow developers to take full advantage of the FluentChip technology library.