80-0206-R Datasheet, PDF (1/49 Pages) List of Unclassifed Manufacturers – Speech Recognition Processor

RSC-4128
Speech Recognition Processor
Data Sheet
General Description
The RSC-4128 represents Sensory’s next generation
speech and analog I/O mixed signal processor. The
RSC-4128 is designed to bring high performance
speech I/O features to cost sensitive embedded and
consumer products. Based on an 8-bit
microcontroller, the RSC-4128 integrates speech-
optimized digital and analog processing blocks into a
single chip solution capable of accurate speech
recognition; high quality, low data-rate compressed
speech; and advanced music. Products can use one
or all features in a single application.
The RSC-4128 operates in tandem with the radically
new FluentChip™ technology, offering the best
speech recognition technologies in the industry.
FluentChip™ includes Hidden Markov Model-Neural
Net hybrid speech recognition. Accuracy in all kinds
of noise is dramatically improved. New Speaker
Verification technology is perfect for voice password
security applications that must work in noisy
environments. New high quality compressed speech
technology reduces data rates by 5 times. New 8-
voice MIDI-compatible music includes drum tracks,
effectively increasing instruments beyond 8.
Simultaneous music and speech round out the
FluentChip™ technology.
FluentChip™ technology tools also support the
revolutionary capability of creating speaker
independent recognition sets by simply typing in the
desired recognition vocabulary! A few keystrokes
creates a recognition set in seconds without the wait
or cost of recording sessions to train the recognizer,
speeding time to sales.
A new and unique Audio Wakeup feature listens
while the RSC-4128 is in power down mode. When
an audio event such as a clap or whistle occurs,
Audio Wakeup will wakeup the RSC-4128 for speech
or application tasks. Audio Wakeup is perfect for
battery applications that require continuous listening
and long battery life.
In addition to best-in-class recognition performance,
the RSC-4128 provides further on-chip integration of
features. A complete speech I/O application can be
built with as few additional parts as a clock crystal,
speaker, microphone, and few resistors and
capacitors.
Moreover, the RSC-4128 provides an unprecedented
level of cost effective system-on-chip (SOC)
integration, enabling many applications that require
DSP and/or audio processing. The RSC-4128 may
be used as a general-purpose mixed signal
processor platform for custom algorithms,
technologies and applications.
Features
Full Range of FluentChip™ Capabilities
 Noise-robust Speaker Independent and Speaker
Dependent recognition
Many languages now available for international use
 Speaker Verification – voice password biometric security
 Word Spotting and Continuous Listening recognition
options
High quality, 2.4-7.8 kbps speech synthesis & sound
effects, with Sensory SX™ synthesis technology
8 voice MIDI-compatible music synthesis coincident with
speech; drum track feature enables additional voices
Voice Record & Playback (voice memo)
Audio Wake Up from sleep with whistles or claps
Touch Tone (DTMF) output
Integrated Single-Chip Solution
8-bit microcontroller
128K bytes ROM
16 bit ADC, 10 bit DAC & PWM, and microphone pre-
amplifier
Independent, programmable Digital Filter engine
4.8 KBytes total RAM (262 bytes “user” application RAM)
Five timers (3 GP, 1 Watchdog, 1 Multi Tasking)
Twin-DMA, Vector Math accelerator, and Multiplier
Built-in Analog Comparator Unit (4 inputs)
External memory bus: 20-bit Address(1Mbyte), 8-bit Data
On chip storage for SD, SV, templates (10 templates)
24 configurable I/O lines with 10 mA (typical) outputs
Code security - no ROM dump capability
Uses low cost 3.58MHz crystal (internal PLL)
Low EMI design for FCC and CE requirements
Fully nested interrupt structure with up to 8 sources
Optional Real Time Clock
Long Battery Life
2.4 – 3.6V operation
12mA (typical) operating current at 3V
2 low power modes; 1 µA typical sleep current
Full Suite of Quick & Powerful Tools
Quick Text-to-SI (T2SI™) text entry to build noise robust
SI recognition sets: low cost & push-button–no recording!
QuickSynthesis™ 4 for push-button speech compression
Integrated Development Environment, C Compiler,
Debugger & In Circuit Emulator from Phyton, Inc.
© 2006 Sensory Inc.
P/N 80-0206-R
1