SPEECH Device Cntrl
-
Upload
sirish-dummula -
Category
Documents
-
view
232 -
download
0
Transcript of SPEECH Device Cntrl
-
8/2/2019 SPEECH Device Cntrl
1/37
1. INTRODUCTION
The speech recognition system is a completely assembled and easy to use programmable speech
recognition circuit. Programmable, in the sense that you train the words (or vocal utterances) youwant the circuit to recognize. This board allows you to experiment with many facets of speechrecognition technology. It has 8 bit data out which can be interfaced with any microcontroller for
further development. Some of interfacing applications which can be made are controlling home
appliances, robotics movements, Speech Assisted technologies, Speech to text translation, andmany more.
Voice based device control is an interesting voice based project, mainly useful for
industrial applications, surveillance applications. This project gives exact concept of controlling
a device by a voice instruction. This project is the first step to design of voice based deviceautomation projects.
The use of Device control systems in the industrial environment or automation
application is an important issue so that the user can find a balance between their devices and itsusage at particular time only. A speech recognizes process to operate the ON/OFF the particular
device period of work enables reliability to compute them, avoiding interest conflicts between
the devices and its usage. The ordinary speech control Device systems use a PIC16F877Amicrocontroller to identify the particular key.
According to that key, devices will be ON /off .These systems can be easily deceived
because the user can be operated from the microcontroller to another microcontroller using
ULN2003 driver and relays. In industrial, users do not need to go and switch ON/OFF to the
particular device, neither to monitor device status. By saying particular word to the
microcontroller. In this project, it is proposed microcontroller to microcontroller interface
scheme that improves a user-friendly and flexible interface to the I/O devices.
Technology: Speech recognition:
Speech recognition is classified into two categories, speaker dependent and speaker independent.
Speaker dependent systems are trained by the individual who will be using the system.
Speaker independent is a system trained to respond to a word regardless of who speaks. Speech
recognition systems have another constraint concerning the style of speech they can recognize.
They are three styles of speech: isolated, connected and continuous. Isolated speech recognition
systems can just handle words that are spoken separately. This is the most common speech
recognition systems available today.
-
8/2/2019 SPEECH Device Cntrl
2/37
Connected is a half way point between isolated word and continuous speech recognition. Allows
users to speak multiple words. The HM2007 can be set up to identify words or phrases 1.92
seconds in length.
2. Block diagram
PIC
Microcontroller
Voice
Recognition
Module
Microphone
Power supply to all
sections
Step
down
T/F
Bridge
Rectifier
Filter
Circuit
Regulato
r
CLK
RESETULN
2003ADIV 1
DIV 4
DIV 2
DIV 3
-
8/2/2019 SPEECH Device Cntrl
3/37
2.1 BLOCK DIAGRAM EXPLANATION
The PIC microcontroller contains five ports. In this project one port is dedicated for
speech recognition. Relays are interfaced through ULN driver circuit to control the devices. A
simple yet powerful program is written in c language and burned into the microcontroller to
record and accept voice instructions and to control the device.
This project uses regulated 5V, 500mA power supply. 7805 three terminal voltage
regulator is used for voltage regulation. Bridge type full wave rectifier is used to rectify the ac
out put of secondary of 230/12V step down transformer.
-
8/2/2019 SPEECH Device Cntrl
4/37
3 .CIRCUIT DIAGARAM
VOICE RECOGNITION KIT USING HM2007
-
8/2/2019 SPEECH Device Cntrl
5/37
Introduction
Speech Recognition System
The speech recognition system is a completely assembled and easy to use programmable speechrecognition circuit. Programmable, in the sense that you train the words (or vocal utterances) you
want the circuit to recognize. This board allows you to experiment with many facets of speech
recognition technology. It has 8 bit data out which can be interfaced with any microcontroller forfurther development. Some of interfacing applications which can be made are controlling home
appliances, robotics movements, Speech Assisted technologies, Speech to text translation, and
many more.
Features
Self-contained stand alone speech recognition circuit
User programmable Up to 20 word vocabulary of duration two second each
Multi-lingual Non-volatile memory back up with 3V battery onboard.
Will keep the speech recognition data in memory even after power off. Easily interfaced to control external circuits & appliances
Specification
Input Voltage - 9 to 15 V DC Use a commonly available 12V 500ma DC Adapter
Output Data - 8 bits at 5V Logic Level
Interface - Any microcontroller like 8051, PIC or AVR can be interfaced to data port to interpret
ApplicationsThere are several areas for application of voice recognition technology. Speech controlled appliances and toys
Speech assisted computer games
Speech assisted virtual reality Telephone assistance systems
Voice recognition security
Speech to speech translation
Introduction
Speech recognition will become the method of choice for controlling appliances, toys, tools and
computers. At its most basic level, speech controlled appliances and tools allow the user toperform parallel tasks (i.e. hands and eyes are busy elsewhere) while working with the tool or
appliance. The heart of the circuit is the HM2007 speech recognition IC. The IC can recognize
20 words, each word a length of 1.92 seconds
Using the System
-
8/2/2019 SPEECH Device Cntrl
6/37
The keypad and digital display are used to communicate with and program the HM2007 chip.
The keypad is made up of 12 normally open momentary contact switches. When the circuit is
turned on, 00 is on the digital display, the red LED (READY) is lit and the circuit waits for acommand.
Training Words for RecognitionPress 1 (display will show 01 and the LED will turn off) on the keypad, then press the
TRAIN key ( the LED will turn on) to place circuit in training mode, for word one. Say the target
word into the onboard microphone (near LED) clearly. The circuit signals acceptance of thevoice input by blinking the LED off then on. The word (or utterance) is now identified as the
01 word. If the LED did not flash, start over by pressing 1 and then TRAIN key. You may
continue training new words in the circuit. Press 2 then TRN to train the second word and so
on. The circuit will accept and recognize up to 20 words (numbers 1 through 20). It is notnecessary to train all word spaces. If you only require 10 target words that are all you need to
train.
Testing Recognition:Repeat a trained word into the microphone. The number of the word should be displayed on the
digital display. For instance, if the word directory was trained as word number 20, saying theword directory into the microphone will cause the number 20 to be displayed.
Error Codes:
The chip provides the following error codes.55 = word to long
66 = word to short
77 = no match
Clearing Memory
To erase all words in memory press 99 and then CLR. The numbers will quickly scroll by onthe digital display as the memory is erased.
Changing & Erasing Words
Trained words can easily be changed by overwriting the original word. For instances suppose
word six was the word Capital and you want to change it to the word State. Simply retrain
the word space by pressing 6 then the TRAIN key and saying the word State into the
microphone. If one wishes to erase the word without replacing it with another word press theword number (in this case six) then press the CLR key. Word six is now erased.
Simulated Independent Recognition
The speech recognition system is speaker dependant, meaning that the voice that trained the
system has the highest recognition accuracy. But you can simulate independent speech
recognition. To make the recognition system simulate speaker independence one uses more thanone word space for each target word. Now we use four word spaces per target word. Therefore
we obtain four different enunciations of each target word. (Speaker independent). The word
spaces 01, 02, 03 and 04 are allocated to the first target word. We continue do this for the
remaining word space. For instance, the second target word will use the word spaces 05, 06, 07
-
8/2/2019 SPEECH Device Cntrl
7/37
and 08. We continue in this manner until all the words are programmed. If you are experimenting
with speaker independence use different people when training a target word. This will enable the
system to recognize different voices, inflections and enunciations of the target word. The moresystem resources that are allocated for independent recognition the more robust the circuit will
become. If you are experimenting with designing the most robust and accurate system possible,
train target words using one voice with different inflections and enunciation's of the target word.
Homonyms
Homonyms are words that sound alike. For instance the words cat, bat, sat and fat sound alike.Because of their like sounding nature they can confuse the speech recognition circuit. When
choosing target words for your system do not use homonyms.
The Voice with Stress & Excitement
Stress and excitement alters ones voice. This affects the accuracy of the circuits recognition.
For instance assume you are sitting at your workbench and you program the target words like
fire, left, right, forward, etc., into the circuit. Then you use the circuit to control a flight simulator
game, Doom or Duke Nukem. Well, when youre playing the game youll likely be yellingFIRE! Fire! ...FIRE!! ...LEFT go RIGHT!. In the heat of the action youre voice will
sound much different than when you were sitting down relaxed and programming the circuit. Toachieve higher accuracy word recognition one needs to mimic the excitement in ones voice when
programming the circuit. These factors should be kept in mind to achieve the high accuracy
possible from the circuit. This becomes increasingly important when the speech recognition
circuit is taken out of the lab and put to work in the outside world.
Error Codes
When interfacing the external circuit through its data bus, the decoding circuit must recognizethe word numbers from error codes. So the circuit must be designed to recognize error codes
55, 66 and 77 and not confuse them with word spaces 5, 6 and 7.
Voice Security System
This circuit isnt designed for a voice security system in a commercial application, but that
should not prevent anyone from experimenting with it for that purpose. A common approach isTo use three or four keywords that must be spoken and recognized in sequence in order to open a
lock or allow entry.
Aural Interfaces
Its been found that mixing visual and aural information is not effective. Products that require
visual confirmation of an aural command grossly reduces efficiency. To create an effective AUI
products need to understand (recognize) commands given in an unstructured and efficientmethods. The way in which people typically communicate verbally.
Learning to Listen
The ability to listen to one person speak among several at a party is beyond the capabilities of
todays speech recognition systems. Speech recognition systems can not (as of yet) separate and
filter out what should be considered extraneous noise. Speech recognition does not understand
speech. Understanding the meaning of words is a higher intellectual function.
-
8/2/2019 SPEECH Device Cntrl
8/37
Because a circuit can respond to a vocal command doesnt mean it understands the command
spoken. In the future, voice recognition systems may have the ability to distinguish nuances of
speech and meanings of words, to Do what I mean, not what I say!
Speaker Dependent / Speaker Independent
Speech recognition is divided into two broad processing categories; speaker dependent andspeaker independent. Speaker dependent systems are trained by the individual who will be using
the system. These systems are capable of achieving a high command count and better than 95%
accuracy for word recognition. The drawback to this approach is that the system only respondsaccurately only to the individual who trained the system. This is the most common approach
employed in software for personal computers. Speaker independent is a system trained to
respond to a word regardless of who speaks. Therefore the system must respond to a large
variety of speech patterns, inflections and enunciation's of the target word. The command wordcount is usually lower than the speaker dependent however high accuracy can still be maintain
within processing limits. Industrial applications more often require speaker independent voice
recognition systems.
Recognition Style
In addition to the speaker dependent/independent classification, speech recognition also contendswith the style of speech it can recognize. They are three styles of speech: isolated, connected and
continuous. Isolated: Words are spoken separately or isolated. This is the most common speech
recognition system available today. The user must pause between each word and command
spoken. Connected: This is a half way point between isolated word and continuous speechrecognition. It permits users to speak multiple words. The HM2007 can be set up to identify
words or phrases 1.92 seconds in length. This reduces the word recognition dictionary number to
20. Continuous: This is the natural conversational speech we use to in everyday life. It isextremely difficult for a recognizer to sift through the sound as the words tend to merge together.
For instance, "Hi, how are you doing?" to a computer sounds like "Hi,.howyadoin" Continuous
speech recognition systems are on the market and are under continual development.
More on the HM2007 Chip
The HM2007 is a CMOS voice recognition LSI (Large Scale Integration) circuit. The chipcontains an analog front end, voice analysis, regulation, and system control functions. The chip
may be used in a stand alone or CPU connected.
Features:
Single chip voice recognition CMOS LSI
Speaker dependent
External RAM support Maximum 40 word recognition (.96 second)
Maximum word length 1.92 seconds (20 word)
Microphone support Manual and CPU modes available
Response time less than 300 milliseconds
5V power supply
-
8/2/2019 SPEECH Device Cntrl
9/37
3.1 RELAYS
A relay is usually an electromechanical device that is actuated by an electrical current.
The current flowing in one circuit causes the opening or closing of another circuit. Relays are
like remote control switches and are used in many applications because of their relative
simplicity, long life, and proven high reliability. Relays are used in a wide variety of applications
throughout industry, such as in telephone exchanges, digital computers and automation systems.
Highly sophisticated relays are utilized to protect electric power systems against trouble and
power blackouts as well as to regulate and control the generation and distribution of power. In
the home, relays are used in refrigerators, washing machines and dishwashers, and heating and
air-conditioning controls. Although relays are generally associated with electrical circuitry, there
are many other types, such as pneumatic and hydraulic. Input may be electrical and output
directly mechanical, or vice versa.
All relays contain a sensing unit, the electric coil, which is powered by AC or DC
current. When the applied current or voltage exceeds a threshold value, the coil activates the
armature, which operates either to close the open contacts or to open the closed contacts. When a
power is supplied to the coil, it generates a magnetic force that actuates the switch mechanism.
The magnetic force is, in effect, relaying the action from one circuit to another. The first circuit
is called the control circuit; the second is called the load circuit.
-
8/2/2019 SPEECH Device Cntrl
10/37
On/Off Control: Example: Air conditioning control, used to limit and control a high
power load, such as a compressor Limit Control:
Example: Motor Speed Control, used to disconnect a motor if it runs slower or faster than the
desired speed
Logic Operation: Example: Test Equipment, used to connect the instrument to a number
of testing points on the device under test.
Electromechanical Relays:
In our project we will be using an electromechanical relay, which will be a 5 pin relay
and the working of the relay will be like as. The general-purpose relay is rated by the amount of
current its switch contacts can handle. Most versions of the general-purpose relay have one to
eight poles and can be single or double throw. These are found in computers, copy machines, and
other consumer electronic equipment and appliances.
-
8/2/2019 SPEECH Device Cntrl
11/37
Load Types:
Load parameters include the maximum permissible voltage and the maximum permissible
current. The relay can handle both volts and amps. Both the size of the load and its type are
important. There are four types of loads:
1.) Resistive, 2.) Inductive, 3.) AC or DC, and 4.) High or Low Inrush.
1.) Resistive Load is one that primarily offers resistance to the flow of current. Examples of
resistive loads include electric heaters, ranges and ovens, toasters and irons.
2.) Inductive Loads include power drills, electric mixers, fans, sewing machines and vacuum
cleaners. Relays that are going to be subjected to high-inrush inductive loads, such as an AC
motor, will often be rated in horsepower, rather than in volts and amps. This rating reflects the
amount of power the relay contacts can handle at the moment the device is turned on (or
switched).
3.) AC or DC This affects the contacts circuit of the relay (due to EMF) and the timing
sequencing. And may result in performance issues in the switching capacity of the relay for
different load types (I.e. resistive, inductive, etc.).
-
8/2/2019 SPEECH Device Cntrl
12/37
4.) High or Low Inrush - Some load types draw significantly higher amounts of current
(amperage) when first turned then they do when the circuit later stabilizes (loads may also
pulsate as the circuit continues operating, thus increasing and decreasing the current). An
example of a high inrush load is a light bulb, which may draw 10 or more times its normal
operating current when first turned on (some manufacturers refer to this as lamp load).
3.2 INTERNAL OPERATION OF MECHANICAL RELAYS
Standard: Single Side Stable with any of the following three different methods for closing
contacts:
1. Flexure Type: The armature actuates the contact spring directly, and the contact is driven into
a stationary contact, closing the circuit.
2. Lift-off Type: The moveable piece is energized by the armature, and the contact closes
3. Plunger Type: The lever action caused by the energization of the armature produces a long
stroke action. Reed: A Single Side Stable Contact that involves low contact pressure and a
simple contact point.
4. Polarized: Can be either a single side stable or dual-winding. A permanent magnet is used to
either attract or repel the armature that controls the contact. A definite polarity (+ or -) is required
By the relay coil. The latching option makes a polarized relay dual-winding, meaning it remains
in the current state after the coil is de-energized.
-
8/2/2019 SPEECH Device Cntrl
13/37
3.3 RELAY DRIVER(ULN2003)
The ULN2001A, ULN2002A, ULN2003 and ULN2004Aare high Voltage, high current
Darlington arrays each containing seven open collector Darlington pairs with common emitters.
Each channel rated at 500mAand can withstand peak currents of 600mA.Suppressiondiodesare
included for inductive load driving and the inputs are pinned opposite the outputs to simplify
board layout.
These versatile devices are useful for driving a wide range of loads including solenoids,
relays DC motors; LED displays filament lamps, thermal print heads and high power buffers.
The ULN2001A/2002A/2003A and 2004A are supplied in 16 pin plastic DIP packages with a
copper lead frame to reduce thermal resistance. They are available also in small outline package
(SO-16) as ULN2001D/2002D/2003D/2004D.
FEATURES OF DRIVER:
SEVENDARLINGTONS PER PACKAGE.
OUTPUT CURRENT 500mA PER DRIVER (600mA PEAK)
OUTPUT VOLTAGE 50V.
-
8/2/2019 SPEECH Device Cntrl
14/37
INTEGRATED SUPPRESSION DIODES FOR
INDUCTIVE LOADS.
OUTPUTS CAN BE PARALLELED FOR
HIGHERCURRENT.
TTL/CMOS/PMOS/DTLCOMPATIBLE INPUTS.
INPUTS PINNED OPPOSITE OUTPUTS TO
SIMPLIFYLAYOUT
PIN CONNECTION:
-
8/2/2019 SPEECH Device Cntrl
15/37
3.4 EMBEDDED SYSTEMS:
Embedded System is a combination of hardware and software used to achieve a single
specific task. An embedded system is a microcontroller-based, software driven, reliable, real-
time control system, autonomous, or human or network interactive, operating on diverse physical
variables and in diverse environments and sold into a competitive and cost conscious market.
-
8/2/2019 SPEECH Device Cntrl
16/37
An embedded system is not a computer system that is used primarily for processing,
not a software system on PC or UNIX, not a traditional business or scientific
application. High-end embedded & lower end embedded systems. High-end
embedded
Systems and hardware layout designed for the specific purpose. Examples Small controllers and
devices in our everyday life like Washing Machine, Microwave Ovens, where they are
embedded in.
System Design Calls
-
8/2/2019 SPEECH Device Cntrl
17/37
The Embedded System Design Cycle
V Diagram
In this place we need to discuss the role of simulation software, real-time systems and data
acquisition in dynamic test applications. Traditional testing is referred to as static testing
where functionality of components is tested by providing known inputs and measuring outputs.
Today there is more pressure to get products to market faster and reduce design cycle times.
This has led to a need for dynamic testing where components are tested while in use with the
entire system either real or simulated. Because of cost and safety concerns, simulating the rest
of the the system with real-time hardware is preferred to testing components in the actual real
system.
The diagram shown on this slide is the V Diagram that is often used to describe the
development cycle. Originally developed to encapsulate the design process of software
applications, many different versions of this diagram can be found to describe different product
design cycles. Here we have shown one example of such a diagram representing the design
cycle of embedded control applications common to automotive, aerospace and defense
applications.
In this diagram the general progression in time of the development stages is shown from left to
right. Note however that this is often an iterative process and the actual development will not
-
8/2/2019 SPEECH Device Cntrl
18/37
proceed linearly through these steps. The goal of rapid development is to make this cycle as
efficient as possible by minimizing the iterations required for a design. If the x-axis of the
diagram is thought of as time, the goal is to narrow the V as much as possible and thereby
reduce development time.
The y-axis of this diagram can be thought of as the level at which the system components are
considered. Early on in the development, the requirements of the overall system must be
considered. As the system is divided into sub-systems and components, the process becomes
very low-level down to the point of loading code onto individual processors. Afterwards
components are integrated and tested together until such time that the entire system can enter
final production testing. Therefore the top of the diagram represents the high-level system view
and the bottom of the diagram represents a very low-level view.
Notes:
V diagram describes lots of applicationsderived from software development.
Reason for shape, every phase of design requires a complimentary test phase. High-level to low-
level view of application. This is a simplified version. Loop back/ Iterative process, X-axis is
time (sum up).
Characteristics of Embedded System:
An embedded system is any computer system hidden inside a product other than a computer
There will encounter a number of difficulties when writing embedded system software in
addition to those we encounter when we write applications
Throughput Our system may need to handle a lot of data in a short period of time.
ResponseOur system may need to react to events quickly
-
8/2/2019 SPEECH Device Cntrl
19/37
TestabilitySetting up equipment to test embedded software can be difficult
Debug abilityWithout a screen or a keyboard, finding out what the software is doing wrong
(other than not working) is a troublesome problem
Reliability embedded systems must be able to handle any situation without human intervention
Memory space Memory is limited on embedded systems, and you must make the software and
the data fit into whatever memory exists
Program installation you will need special tools to get your software into embedded systems
Power consumption Portable systems must run on battery power, and the software in these
systems must conserve power
Processor hogs computing that requires large amounts of CPU time can complicate the
response problem
Cost Reducing the cost of the hardware is a concern in many embedded system projects;
software often operates on hardware that is barely adequate for the job.
Embedded systems have a microprocessor/ microcontroller and a memory. Some have a serial
port or a network connection. They usually do not have keyboards, screens or disk drives.
Applications:
1. Military and aerospace embedded software applications.
3.5 ABOUT MICROCONTROLLER:
-
8/2/2019 SPEECH Device Cntrl
20/37
The micro-controller is a chip, which has a computer processor with all its support
function, memory (both program storage and RAM), and I/O built in to the device. These built in
functions minimize the need for external circuits and devices to design in the final applications.
Most microcontrollers do not require a substantial amount of time to learn how to
efficiently program them, although many of them which have quirks which you will have to
understand before you attempt to develop your first application.
Along with micro-controllers getting faster, smaller and more power efficient they are
also getting more and more features. Often, the first version of micro-controller will just have
memory and digital I/O, but as the device family matures, more and more pat numbers with
varying features will be available.
PIC 16F877A:
Microcontroller Core Features:
High-performance RISC CPU.
Only 35 single word instructions to learn.
All single cycle instructions except for program branches which are two cycle
Operating speed: DC - 20 MHz clock input DC - 200 ns instruction cycle.
Up to 8K x 14 words of FLASH Program Memory, Up to 368 x 8 bytes of Data Memory
(RAM) Up to 256 x 8 bytes of EEPROM data memory.
Pin out compatible to the PIC16C73B/74B/76/77
Interrupt capability (up to 14 sources)
Eight level deep hardware stack
Direct, indirect and relative addressing modes.
-
8/2/2019 SPEECH Device Cntrl
21/37
Power-on Reset (POR).
Power-up Timer (PWRT) and Oscillator Start-up Timer (OST).
Watchdog Timer (WDT) with its own on-chip RC oscillator for reliable operation.
Programmable code-protection.
Power saving SLEEP mode.
Selectable oscillator options.
Low-power, high-speed CMOS FLASH/EEPROM technology.
Fully static design.
In-Circuit Serial Programming (ICSP) .
Single 5V In-Circuit Serial Programming capability.
In-Circuit Debugging via two pins.
Processor read/write access to program memory.
Wide operating voltage range: 2.0V to 5.5V.
High Sink/Source Current: 25 mA.
Commercial and Industrial temperature ranges.
-
8/2/2019 SPEECH Device Cntrl
22/37
PIN DIAGRAM
-
8/2/2019 SPEECH Device Cntrl
23/37
Peripheral Features:
Timer0: 8-bit timer/counter with 8-bit prescaler
-
8/2/2019 SPEECH Device Cntrl
24/37
Timer1: 16-bit timer/counter with prescaler, can be incremented during sleep via external
crystal/clock
Timer2: 8-bit timer/counter with 8-bit period register, prescaler and postscaler
Two Capture, Compare, PWM modules
- Capture is 16-bit, max. Resolution is 12.5 ns
- Compare is 16-bit, max. Resolution is 200 ns
- PWM max. Resolution is 10-bit
10-bit multi-channel Analog-to-Digital converter
Synchronous Serial Port (SSP) with SPI (Master Mode) and I2C (Master/Slave)
Universal Synchronous Asynchronous Receiver Transmitter (USART/SCI) with 9-bit address
detection
Parallel Slave Port (PSP) 8-bits wide, with external RD, WR and CS controls (40/44-pin only)
Brown-out detection circuitry for Brown-out Reset (BOR)
CMOS Technology:
Low-power, high-speed Flash/EEPROM technology.
Fully static design.
Wide operating voltage range (2.0V to 5.5V).
Commercial and Industrial temperature ranges.
Low-power consumption.
-
8/2/2019 SPEECH Device Cntrl
25/37
4. VOICE RECOGNITION KIT USING HM2007Introduction
Speech Recognition System
The speech recognition system is a completely assembled and easy to use programmable speech
recognition circuit. Programmable, in the sense that you train the words (or vocal utterances) youwant the circuit to recognize. This board allows you to experiment with many facets of speech
recognition technology. It has 8 bit data out which can be interfaced with any microcontroller for
further development. Some of interfacing applications which can be made are controlling homeappliances, robotics movements, Speech Assisted technologies, Speech to text translation, and
many more.
Features Self-contained stand alone speech recognition circuit
ser programmable
Up to 20 word vocabulary of duration two second each
Multi-lingual
Non-volatile memory back up with 3V battery onboard.
Will keep the speech recognition data in memory even after power off.
Easily interfaced to control external circuits & appliances
Specification
Input Voltage - 9 to 15 V DC Use a commonly available 12V 500ma DC Adapter
Output Data - 8 bits at 5V Logic Level
Interface - Any microcontroller like 8051, PIC or AVR can be interfaced to data port to interpret
Applications
-
8/2/2019 SPEECH Device Cntrl
26/37
There are several areas for application of voice recognition technology.
Speech controlled appliances and toys
Speech assisted computer games
Speech assisted virtual reality
Telephone assistance systems
Voice recognition security
Speech to speech translation
Introduction
Speech recognition will become the method of choice for controlling appliances, toys, tools andcomputers. At its most basic level, speech controlled appliances and tools allow the user to
perform parallel tasks (i.e. hands and eyes are busy elsewhere) while working with the tool or
Appliance. The heart of the circuit is the HM2007 speech recognition IC. The IC can recognize20 words, each word a length of 1.92 seconds.
Using the SystemThe keypad and digital display are used to communicate with and program the HM2007 chip.
The keypad is made up of 12 normally open momentary contact switches. When the circuit is
Turned on, 00 is on the digital display, the red LED (READY) is lit and the circuit waits for a
Command.
Training Words for Recognition
Press 1 (display will show 01 and the LED will turn off) on the keypad, then press the
TRAIN key (the LED will turn on) to place circuit in training mode, for word one. Say the targetWord into the onboard microphone (near LED) clearly. The circuit signals acceptance of the
Voice input by blinking the LED off then on. The word (or utterance) is now identified as the
01 word. If the LED did not flash, start over by pressing 1 and then TRAIN key.You may continue training new words in the circuit. Press 2 then TRN to train the second
Word and so on. The circuit will accept and recognize up to 20 words (numbers 1 through 20).
It is not necessary to train all word spaces. If you only require 10 target words thats all youNeed to train.
Testing Recognition:
Repeat a trained word into the microphone. The number of the word should be displayed on the
digital display. For instance, if the word directory was trained as word number 20, sayingThe word directory into the microphone will cause the number 20 to be displayed.
Error Codes:
The chip provides the following error codes.55 = word to long
66 = word to short
77 = no match
Clearing Memory
-
8/2/2019 SPEECH Device Cntrl
27/37
To erase all words in memory press 99 and then CLR. The numbers will quickly scroll by on
the digital display as the memory is erased.
Changing & Erasing Words
Trained words can easily be changed by overwriting the original word. For instances suppose
word six was the word Capital and you want to change it to the word State. Simply retrainthe word space by pressing 6 then the TRAIN key and saying the word State into the
microphone. If one wishes to erase the word without replacing it with another word press the
word number (in this case six) then press the CLR key. Word six is now erased.
Simulated Independent Recognition
The speech recognition system is speaker dependant, meaning that the voice that trained the
system has the highest recognition accuracy. But you can simulate independent recognition. To
make the recognition system simulate speaker independence one uses more than one word spacefor each target word. Now we use four word spaces per target word. Therefore we obtain four
different enunciations of each target word. (Speaker independent). The word spaces 01, 02, 03
and 04 are allocated to the first target word. We continue do this for the remaining word space.
For instance, the second target word will use the word spaces 05, 06, 07 and 08. We continue inthis manner until all the words are programmed.
If you are experimenting with speaker independence use different people when training a targetword. This will enable the system to recognize different voices, inflections and enunciations of
the target word. The more system resources that are allocated for independent recognition the
more robust the circuit will become. If you are experimenting with designing the most robust and
accurate system possible, train target words using one voice with different inflections andenunciation's of the target word.
Homonyms
Homonyms are words that sound alike. For instance the words cat, bat, sat and fat sound alike.Because of their like sounding nature they can confuse the speech recognition circuit.
When choosing target words for your system do not use homonyms.
The Voice with Stress & Excitement
Stress and excitement alters ones voice. This affects the accuracy of the circuits recognition.
For instance assume you are sitting at your workbench and you program the target words like
fire, left, right, forward, etc., into the circuit. Then you use the circuit to control a flight simulatorgame, Doom or Duke Nukem. Well, when youre playing the game youll likely be yelling
FIRE! Fire! ...FIRE!! ...LEFT go RIGHT! In the heat of the action youre voice will
sound much different than when you were sitting down relaxed and programming the circuit. To
achieve higher accuracy word recognition one needs to mimic the excitement in ones voice whenprogramming the circuit. These factors should be kept in mind to achieve the high accuracy
possible from the circuit. This becomes increasingly important when the speech recognition
circuit is taken out of the lab and put to work in the outside world.
Error Codes
When interfacing the external circuit through its data bus, the decoding circuit must recognize
the word numbers from error codes. So the circuit must be designed to recognize error codes
55, 66 and 77 and not confuse them with word spaces 5, 6 and 7.
Voice Security System
This circuit isnt designed for a voice security system in a commercial application, but that
should not prevent anyone from experimenting with it for that purpose. A common approach is
-
8/2/2019 SPEECH Device Cntrl
28/37
to use three or four keywords that must be spoken and recognized in sequence in order to open a
lock or allow entry.
Aural Interfaces
Its been found that mixing visual and aural information is not effective. Products that require
visual confirmation of an aural command grossly reduces efficiency. To create an effective AUI
products need to understand (recognize) commands given in an unstructured and efficientmethods. The way in which people typically communicate verbally.
Learning to Listen
The ability to listen to one person speak among several at a party is beyond the capabilities oftodays speech recognition systems. Speech recognition systems cannot (as of yet) separate and
filter out what should be considered extraneous noise. Speech recognition does not understand
speech. Understanding the meaning of words is a higher intellectual function. Because a circuit
can respond to a vocal command doesnt mean it understands the command spoken. In thefuture, voice recognition systems may have the ability to distinguish nuances of speech and
meanings of words, to Do what I mean, not what I say!
Speaker Dependent / Speaker Independent
Speech recognition is divided into two broad processing categories; speaker dependent andspeaker independent. Speaker dependent systems are trained by the individual who will be using
the system. These systems are capable of achieving a high command count and better than 95%accuracy for word recognition. The drawback to this approach is that the system only responds
accurately only to the individual who trained the system. This is the most common approach
employed in software for personal computers. Speaker independent is a system trained to
respond to a word regardless of who speaks. Therefore the system must respond to a largevariety of speech patterns, inflections and enunciation's of the target word. The command word
count is usually lower than the speaker dependent however high accuracy can still be maintain
within processing limits. Industrial applications more often require speaker independent voicerecognition systems.
Recognition Style
In addition to the speaker dependent/independent classification, speech recognition also contendswith the style of speech it can recognize. They are three styles of speech: isolated, connected and
continuous. Isolated: Words are spoken separately or isolated. This is the most common speech
recognition system available today. The user must pause between each word and commandspoken. Connected: This is a half way point between isolated word and continuous speech
recognition. It permits users to speak multiple words. The HM2007 can be set up to identify
words or phrases 1.92 seconds in length. This reduces the word recognition dictionary number to
20. Continuous: This is the natural conversational speech we use to in everyday life. It isextremely difficult for a recognizer to sift through the sound as the words tend to merge together.
For instance, "Hi, how are you doing?" to a computer sounds like "Hi,.howyadoin" Continuous
speech recognition systems are on the market and are under continual development.
More on the HM2007 Chip
The HM2007 is a CMOS voice recognition LSI (Large Scale Integration) circuit. The chip
contains an analog front end, voice analysis, regulation, and system control functions. The chipmay be used in a stand alone or CPU connected.
Features:
Single chip voice recognition CMOS LSI
-
8/2/2019 SPEECH Device Cntrl
29/37
Speaker dependent
External RAM support
Maximum 40 word recognition (.96 second) Maximum word length 1.92 seconds (20 words)
Microphone support
Manual and CPU modes available Response time less than 300 milliseconds
5V power supply
4.1 Analog-to-digital convert
An analog-to-digital converter (abbreviated ADC, A/D orA to D) is a device which converts a
continuous quantity to a discrete digital number. The reverse operation is performed by a digital-
to-analog converter(DAC).
Typically, an ADC is an electronic device that converts an input analog voltage (orcurrent) to
a digital number proportional to the magnitude of the voltage or current. However, some non-
electronic or only partially electronic devices, such as rotary encoders, can also be considered
ADCs.
The digital output may use different coding schemes. Typically the digital output will be a two's
complementbinary number that is proportional to the input, but there are other possibilities. An
encoder, for example, might output a Gray code.
An ADC may provide an isolated measurement. ADCs are also used in quantization of time-
varying signals by turning them into a sequence of digital samples. The result is quantized in
both time and value.
http://en.wikipedia.org/wiki/Discrete_signalhttp://en.wikipedia.org/wiki/Digital-to-analog_converterhttp://en.wikipedia.org/wiki/Digital-to-analog_converterhttp://en.wikipedia.org/wiki/Electronicshttp://en.wikipedia.org/wiki/Voltagehttp://en.wikipedia.org/wiki/Electric_currenthttp://en.wikipedia.org/wiki/Digitalhttp://en.wikipedia.org/wiki/Rotary_encoderhttp://en.wikipedia.org/wiki/Two's_complementhttp://en.wikipedia.org/wiki/Two's_complementhttp://en.wikipedia.org/wiki/Gray_codehttp://en.wikipedia.org/wiki/Signal_(information_theory)http://en.wikipedia.org/wiki/Signal_(information_theory)http://en.wikipedia.org/wiki/Discrete_signalhttp://en.wikipedia.org/wiki/Digital-to-analog_converterhttp://en.wikipedia.org/wiki/Digital-to-analog_converterhttp://en.wikipedia.org/wiki/Electronicshttp://en.wikipedia.org/wiki/Voltagehttp://en.wikipedia.org/wiki/Electric_currenthttp://en.wikipedia.org/wiki/Digitalhttp://en.wikipedia.org/wiki/Rotary_encoderhttp://en.wikipedia.org/wiki/Two's_complementhttp://en.wikipedia.org/wiki/Two's_complementhttp://en.wikipedia.org/wiki/Gray_codehttp://en.wikipedia.org/wiki/Signal_(information_theory)http://en.wikipedia.org/wiki/Signal_(information_theory) -
8/2/2019 SPEECH Device Cntrl
30/37
CIRCUIT DIAGRAM
FIG4.2 POWER SUPPLY UNIT
POWER SUPPLY UNIT COSISTS OF FOLLOWING UNITS
1) Step down transformer
2) Rectifier unit
3) Input filter
4) Regulator unit
v) Output filter
4.3 STEP DOWN TRANSFORMER
-
8/2/2019 SPEECH Device Cntrl
31/37
The Step down Transformer is used to step down the main supply voltage from 230V AC
to lower value. This 230 AC voltage cannot be used directly, thus it is stepped down. The
Transformer consists of primary and secondary coils. To reduce or step down the voltage, the
transformer is designed to contain less number of turns in its secondary core. The output from
the secondary coil is also AC waveform. Thus the conversion from AC to DC is essential. This
conversion is achieved by using the Rectifier Circuit/Unit.
Step down transformers can step down incoming voltage, which enables you to have
the correct voltage input for your electrical needs. For example, if our equipment has been
specified for input voltage of 12 volts, and the main power supply is 230 volts, we will need a
step down transformer, which decreases the incoming electrical voltage to be compatible with
your 12 volt equipment.
4. 4 RECTIFIER UNIT
The Rectifier circuit is used to convert the AC voltage into its corresponding DC voltage.
There are Half-Wave, Full-Wave and bridge Rectifiers available for this specific function. The
most important and simple device used in Rectifier circuit is the diode. The simple function of
the diode is to conduct when forward biased and not to conduct in reverse bias.
Bridge rectifier: A bridge rectifier makes use of four diodes in a bridge arrangement to achieve
full-wave rectification. This is a widely used configuration, both with individual diodes wired as
shown and with single component bridges where the diode bridge is wired internally.
-
8/2/2019 SPEECH Device Cntrl
32/37
A diode bridge or bridge rectifier is an arrangement of four diodes in a bridge
configuration that provides the same polarity of output voltage for either polarity of input
voltage. When used in its most common application, for conversion ofalternating current (AC)
input into direct current (DC) output, it is known as a bridge rectifier. A bridge rectifier provides
full-wave rectification from a two-wire AC input, resulting in lower cost and weight as compared
to a center-tappedtransformerdesign.
The Forward Bias is achieved by connecting the diodes positive with positive of the
battery and negative with batterys negative. The efficient circuit used is the Full wave Bridge
rectifier circuit. The output voltage of the rectifier is in rippled form, the ripples from the
obtained DC voltage are removed using other circuits available. The circuit used for removing
the ripples is called Filter circuit.
4.5 INPUT FILTER
Capacitors are used as filter. The ripples from the DC voltage are removed and pure DC
voltage is obtained. And also these capacitors are used to reduce the harmonics of the input
voltage. The primary action performed by capacitor is charging and discharging. It charges in
positive half cycle of the AC voltage and it will discharge in negative half cycle. So it allows
http://en.wikipedia.org/wiki/Diodehttp://en.wikipedia.org/wiki/Bridge_circuithttp://en.wikipedia.org/wiki/Polarity_(physics)http://en.wikipedia.org/wiki/Volthttp://en.wikipedia.org/wiki/Alternating_currenthttp://en.wikipedia.org/wiki/Direct_currenthttp://en.wikipedia.org/wiki/Rectifierhttp://en.wikipedia.org/wiki/Rectifierhttp://en.wikipedia.org/wiki/Center_taphttp://en.wikipedia.org/wiki/Transformerhttp://en.wikipedia.org/wiki/Diodehttp://en.wikipedia.org/wiki/Bridge_circuithttp://en.wikipedia.org/wiki/Polarity_(physics)http://en.wikipedia.org/wiki/Volthttp://en.wikipedia.org/wiki/Alternating_currenthttp://en.wikipedia.org/wiki/Direct_currenthttp://en.wikipedia.org/wiki/Rectifierhttp://en.wikipedia.org/wiki/Rectifierhttp://en.wikipedia.org/wiki/Center_taphttp://en.wikipedia.org/wiki/Transformer -
8/2/2019 SPEECH Device Cntrl
33/37
only AC voltage and does not allow the DC voltage. The 1000f capacitor serves as a "reservoir"
which maintains a reasonable input voltage to the 7805 throughout the entire cycle of the ac line
voltage. The four rectifier diodes keep recharging the reservoir capacitor on alternate half-cycles
of the line voltage, and the capacitor is quite capable of sustaining any reasonable load in
between charging pulses. This filter is fixed before the regulator. Thus the output is free from
ripples. Input side the low pass filter has been used.
Low pass filter:
One simple electrical circuit that will serve as a low-pass filter consists of a resistorin
series with a load, and a capacitorin parallel with the load. The capacitor exhibits reactance, and
blocks low-frequency signals, causing them to go through the load instead. At higher frequencies
the reactance drops, and the capacitor effectively functions as a short circuit. The combination of
resistance and capacitance gives you the time constantof the filter = RC (represented by the
http://en.wikipedia.org/wiki/Electrical_circuithttp://en.wikipedia.org/wiki/Electrical_circuithttp://en.wikipedia.org/wiki/Resistorhttp://en.wikipedia.org/wiki/External_electric_loadhttp://en.wikipedia.org/wiki/Capacitorhttp://en.wikipedia.org/wiki/Reactance_(electronics)http://en.wikipedia.org/wiki/Time_constanthttp://en.wikipedia.org/wiki/Time_constanthttp://en.wikipedia.org/wiki/Electrical_circuithttp://en.wikipedia.org/wiki/Resistorhttp://en.wikipedia.org/wiki/External_electric_loadhttp://en.wikipedia.org/wiki/Capacitorhttp://en.wikipedia.org/wiki/Reactance_(electronics)http://en.wikipedia.org/wiki/Time_constant -
8/2/2019 SPEECH Device Cntrl
34/37
Greek lettertau). The break frequency, also called the turnover frequency orcutoff frequency (in
hertz), is determined by the time constant: or equivalently (in radians per second):
One way to understand this circuit is to focus on the time the capacitor takes to charge. It
takes time to charge or discharge the capacitor through that resistor:
At low frequencies, there is plenty of time for the capacitor to charge up to
practically the same voltage as the input voltage.
At high frequencies, the capacitor only has time to charge up a small amount
before the input switches direction. The output goes up and down only a small fraction of the
amount the input goes up and down. At double the frequency, there's only time for it to charge
up half the amount.
4.6 REGULATOR UNIT
7805 REGULATOR
Regulator regulates the output voltage to be always constant. The output voltage is
maintained irrespective of the fluctuations in the input AC voltage. As and then the AC voltage
changes, the DC voltage also changes. Thus to avoid this Regulators are used. Also when the
internal resistance of the power supply is greater than 30 ohms, the output gets affected. Thus
this can be successfully reduced here. Meanwhile it also contains current-limiting circuitry and
thermal overload protection, so that the IC won't be damaged in case of excessive load current; it
http://en.wikipedia.org/wiki/Tauhttp://en.wikipedia.org/wiki/Tauhttp://en.wikipedia.org/wiki/Cutoff_frequencyhttp://en.wikipedia.org/wiki/Cutoff_frequencyhttp://en.wikipedia.org/wiki/Radianshttp://en.wikipedia.org/wiki/Tauhttp://en.wikipedia.org/wiki/Cutoff_frequencyhttp://en.wikipedia.org/wiki/Radians -
8/2/2019 SPEECH Device Cntrl
35/37
will reduce its output voltage instead. The regulators are mainly classified for low voltage and
for high voltage. Further they can also be classified as:
1) Positive regulator
Input pin
Ground pin
Output pin
It regulates the positive voltage.
2) Negative regulator
Ground pin
Input pin
Output pin
It regulates the negative voltage.
7805 VOLTAGE REGULATOR:
The 7805 provides circuit designers with an easy way to regulate DC voltages to 5v.
Encapsulated in a single chip/package (IC), the 7805 is a positive voltage DC regulator that has
only 3 terminals. They are: Input voltage, Ground, Output Voltage.
-
8/2/2019 SPEECH Device Cntrl
36/37
BIBILOGRAPHY
http://www.Wikipedia.com
http://eed.hutech.edu.vn/Datasheet/HM2007.pdf
http://www.nskelectronics.com
http://eed.hutech.edu.vn/Datasheet/HM2007.pdfhttp://www.nsk/http://eed.hutech.edu.vn/Datasheet/HM2007.pdfhttp://www.nsk/ -
8/2/2019 SPEECH Device Cntrl
37/37
http://www.microchip.com
http://www.google.com
http://www.microchip.com/http://www.google.com/http://www.microchip.com/http://www.google.com/