rsc-164 ETC-unknow, rsc-164 Datasheet - Page 2

• Manufacturer Part Number: rsc-164
• Description: General Purpose Microcontroller Featuring Speech Recognition, Speech & Music Synthesis, Speaker Verification And Audio Record/playback
• Manufacturer: ETC-unknow

RSC-164
RSC-164 OVERVIEW
The RSC-164 is a member of the Interactive Speech™
line of products from Sensory.
performance 8-bit microcontroller with on-chip A/D,
D/A, RAM and ROM. The RSC-164 is designed to bring
a high degree of integration and versatility into low-cost,
power-sensitive consumer applications.
Various functional units have been integrated onto the
CPU core in order to reduce total system cost and
increase system reliability without degrading system
performance. The RSC-164 delivers 4 MIPS of integer
performance at 14.32 MHz providing maximum
performance at minimum cost.
The CPU core embedded in the RSC-164 is an 8-bit,
variable-length-instruction,
instruction set is loosely based on Intel’s 8051 , and has
a variety of addressing mode mov instructions. The RSC-
164 processor avoids the limitations of dedicated A, B,
and DPTR registers by having completely symmetrical
source and destinations for all instructions. The 384 bytes
of internal RAM are organized as a Register Space.
SPEECH RECOGNITION
The RSC-164 uses a neural network to perform speaker-
independent or speaker-dependent speech recognition.
Speaker-dependent recognition requires external memory
to store speech recognition information (e.g., SRAM,
Flash Memory).
requires on-chip or off-chip ROM to store the words to be
recognized. The RSC-164 has several additional speech
recognition features as described below.
Continuous listening allows the chip to continuously
listen for a specific word. With this feature a product can
be used in a normal environment and only “activates”
when a specific word, preceded by quiet, is spoken.
2
Microphone
Speaker-independent recognition
Preamp and
gain control
microcontroller.
From the Interactive Speech™ Line of Products
It features a high-
Digital Logic
Multiplexer
ADC
AGC
The
Purpose I/O
General
Microcontroller
Oscillator
Consecutive entry allows the chip to handle several voice
inputs in succession as long as each input is surrounded
by one-half second of quiet.
SPEECH AND MUSIC SYNTHESIS
The RSC-164 provides high-quality speech synthesis by
using a hybrid of a time-domain compression scheme
that improves on conventional ADPCM and a customized
reuse of sounds. Speech synthesis requires on-chip or
off-chip ROM to store audio sounds for synthesis.
The RSC-164 provides high-quality, low-cost four-voice
music synthesis which allows multiple, simultaneous
instruments for harmonizing. Music synthesis has low
ROM requirements - a 2-3 minute song requires under 5
kbytes of incremental memory. The RSC-164 uses a
MIDI-like system to generate music.
RECORD AND PLAYBACK
The RSC-164 can perform audio record and playback at
various compression levels depending on the quantity
and quality of playback desired. Data rates of under
14,000 bits per second are achievable while maintaining
very high quality reproduction.
performs silence removal to improve sound quality and
reduce memory requirements.
SPEAKER VERIFICATION
The RSC-164 can also perform text-dependent speaker
verification. After a speaker trains the chip on a specific
word, the chip is able to identify whether that word is
spoken by the original speaker, thus providing biometric
security.
POWER
External
Memory
ROM
RAM
DAC
RSC-164
AMP
Speaker
The RSC-164 also
DATA SHEET