Engineers Garage

  • Projects and Tutorials
    • Electronic Projects
      • 8051
      • Arduino
      • ARM
      • AVR
      • PIC
      • Raspberry pi
      • STM32
    • Tutorials
    • Circuit Design
    • Project Videos
    • Components
  • Articles
    • Tech Articles
    • Insight
    • Invention Stories
    • How to
    • What Is
  • News
    • Electronic Products News
    • DIY Reviews
    • Guest Post
  • Forums
    • EDABoard.com
    • Electro-Tech-Online
    • EG Forum Archive
  • Digi-Key Store
    • Cables, Wires
    • Connectors, Interconnect
    • Discrete
    • Electromechanical
    • Embedded Computers
    • Enclosures, Hardware, Office
    • Integrated Circuits (ICs)
    • Isolators
    • LED/Optoelectronics
    • Passive
    • Power, Circuit Protection
    • Programmers
    • RF, Wireless
    • Semiconductors
    • Sensors, Transducers
    • Test Products
    • Tools
  • EE Resources
    • DesignFast
    • LEAP Awards
    • Oscilloscope Product Finder
    • White Papers
    • Webinars
  • EE Learning Center
    • Design Guides
      • WiFi & the IOT Design Guide
      • Microcontrollers Design Guide
      • State of the Art Inductors Design Guide
  • Women in Engineering

Speech Recognition : Classification

By Ashutosh Bhatt

Classification
Speech Recognition (SR) can broadly be classified into two categories:
1.      Small Vocabulary/ Large User Base: Good for automated tele-services like voice activated dialing and IVR, but the usable vocabulary is highly limited in scope to certain specific commands.
2.      Large Vocabulary/ Small User Base: Suited for environments where small group of people is involved. It however requires more rigorous training for that particular user group and gives erroneous results for anyone outside that group.
Types of Speech Recognition
The current methods rely on mathematically analyzing the digitized sound waves and their spectrum properties. The process involves the conversion of the sound waves spoken into the microphone (at 16KHz) into a digital signal through quantization and digitization following the Nyquist-Shannon Sampling theorem, which simply put, requires at least one sample to be collected for each compression and rarefaction consecutively. This means that the frequency of sampling should be at least twice the highest frequency component in the signal. The speech recognition program then follows various algorithms and models to account for variations and compressing the raw speech signal to simplify processing. The initial compression may be achieved through many methods including Fourier Transforms, Perceptual Linear Prediction, Linear Predictive Coding and Mel-Frequency Cepstral Coefficients.
 
There are commonly four common concepts about which speech is recognized:
1.      Template Based: Predefined templates or samples are created and stored. Whenever a user utters a word, it is correlated with all the templates. The one with the highest correlation is then selected as the spoken word. It isn’t flexible enough to understand voice patterns. Discrete Time Warping may be considered as one of these techniques.
2.      Knowledge based: These analyze spectrograms of voice to collect data and create some rules which are indicative of the uttered command. These do not use language knowledge base or speech variations and are generally used for command based systems.
3.      Stochastic: Speech being a highly random phenomenon can be considered to be a piecewise stationary process over which stochastic models can be applied. As stated earlier, this is one of the most popular methods used by commercial programs. Hidden Markov Models are an example of stochastic methods.
4.      Connectionist: Artificial Neural Networks are used to store and extract various coefficients from the speech data over multilayered structures and various neural nets to deduce the spoken word.
 
The performance is generally measured in terms of accuracy and speed. The general scales are that of Single Word Error Rate, which is the misunderstanding of one word in a spoken sentence, and Command Success Rate, which is the accurate interpretation of the spoken command. Different methods always give varying results which further depends on various external factors.
 

 


Filed Under: Recent Articles

 

Questions related to this article?
👉Ask and discuss on Electro-Tech-Online.com and EDAboard.com forums.



Tell Us What You Think!! Cancel reply

You must be logged in to post a comment.

HAVE A QUESTION?

Have a technical question about an article or other engineering questions? Check out our engineering forums EDABoard.com and Electro-Tech-Online.com where you can get those questions asked and answered by your peers!


Featured Tutorials

  • Introduction to Brain Waves & its Types (Part 1/13)
  • Understanding NeuroSky EEG Chip in Detail (Part 2/13)
  • Performing Experiments with Brainwaves (Part 3/13)
  • Amplification of EEG Signal and Interfacing with Arduino (Part 4/13)
  • Controlling Led brightness using Meditation and attention level (Part 5/13)
  • Control Motor’s Speed using Meditation and Attention Level of Brain (Part 6/13)

Stay Up To Date

Newsletter Signup

Sign up and receive our weekly newsletter for latest Tech articles, Electronics Projects, Tutorial series and other insightful tech content.

EE Training Center Classrooms

EE Classrooms

Recent Articles

  • What is a loop calibrator? 
  • What are the battery-selection criteria for low-power design?
  • Key factors to optimize power consumption in an embedded device
  • EdgeLock A5000 Secure Authenticator
  • How to interface a DS18B20 temperature sensor with MicroPython’s Onewire driver

Most Popular

5G 555 timer circuit 8051 ai Arduino atmega16 automotive avr bluetooth dc motor display Electronic Part Electronic Parts Fujitsu ic infineontechnologies integratedcircuit Intel IoT ir lcd led maximintegratedproducts microchip microchiptechnology Microchip Technology microcontroller microcontrollers mosfet motor powermanagement Raspberry Pi remote renesaselectronics renesaselectronicscorporation Research samsung semiconductor sensor software STMicroelectronics switch Technology vishayintertechnology wireless

RSS EDABOARD.com Discussions

  • Passive Harmonics Filter
  • file edit
  • RCF Subwoofer Amplifier PIC16F870-I/SP please help me about hex code
  • Active Balun Design
  • What was before microcontrollers ?

RSS Electro-Tech-Online.com Discussions

  • Control Bare LCD With ATmega328p
  • Need a ducted soldering fan for solder smoke extraction
  • Identify a circuit.
  • Sla ir li ion
  • Question about ultrasonic mist maker
Engineers Garage
  • Analog IC TIps
  • Connector Tips
  • DesignFast
  • EDABoard Forums
  • EE World Online
  • Electro-Tech-Online Forums
  • Microcontroller Tips
  • Power Electronic Tips
  • Sensor Tips
  • Test and Measurement Tips
  • 5G Technology World
  • About Us
  • Contact Us
  • Advertise

Copyright © 2022 WTWH Media LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media
Privacy Policy | Advertising | About Us

Search Engineers Garage

  • Projects and Tutorials
    • Electronic Projects
      • 8051
      • Arduino
      • ARM
      • AVR
      • PIC
      • Raspberry pi
      • STM32
    • Tutorials
    • Circuit Design
    • Project Videos
    • Components
  • Articles
    • Tech Articles
    • Insight
    • Invention Stories
    • How to
    • What Is
  • News
    • Electronic Products News
    • DIY Reviews
    • Guest Post
  • Forums
    • EDABoard.com
    • Electro-Tech-Online
    • EG Forum Archive
  • Digi-Key Store
    • Cables, Wires
    • Connectors, Interconnect
    • Discrete
    • Electromechanical
    • Embedded Computers
    • Enclosures, Hardware, Office
    • Integrated Circuits (ICs)
    • Isolators
    • LED/Optoelectronics
    • Passive
    • Power, Circuit Protection
    • Programmers
    • RF, Wireless
    • Semiconductors
    • Sensors, Transducers
    • Test Products
    • Tools
  • EE Resources
    • DesignFast
    • LEAP Awards
    • Oscilloscope Product Finder
    • White Papers
    • Webinars
  • EE Learning Center
    • Design Guides
      • WiFi & the IOT Design Guide
      • Microcontrollers Design Guide
      • State of the Art Inductors Design Guide
  • Women in Engineering