80-0206-R Datasheet, PDF (6/49 Pages) List of Unclassifed Manufacturers – Speech Recognition Processor

RSC-4128
Data Sheet
There are three programmable, general-purpose 8-bit counters / timers – Timers 1 and 3 are derived from OSC1,
and Timer2 from OSC2. There is also a Watchdog timer that may be used to exit an undesired condition in
program flow, and Multi-tasking timer to allow chip operations to share resources in parallel.
A single chip speech I/O solution may be created with the RSC-4128. An external microphone passes an audio
signal to the preamplifier and ADC to convert the incoming speech signal into digital data. Speech features are
extracted using the Digital Filter engine. The microcontroller CPU processes these speech features using speech
recognition algorithms in firmware, with the help of the “L1” Vector Accelerator and enhanced instruction set. The
resulting speech recognition results may be used to control the consumer product application code, or to output
speech or audio in the form of a dialog with the user of the consumer product. If desired, the output speech or
audio signal from the RSC-4128 is generated by a DAC for external amplification into a speaker, or a PWM capable
of directly driving a speaker at typical consumer product volumes. A typical product will require about $0.30 - $1.00
(in high volume) of additional components, in addition to the RSC-4128.
The RSC-4128 also provides a very cost effective mixed signal platform for general-purpose applications and
development of custom algorithms. A typical general-purpose application will require about $0.30 - $0.50 (in high
volume) of additional components, in addition to the RSC-4128.
6
P/N 80-0206-R
© 2006 Sensory Inc.