Presentation 60

You might also like

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 12

 

                                

 Technical Seminar on
   Speech Recognition

                               
    Guided by:                                                                       Presented by
    Dr.  A. A. Khodaskar                                                     Mrunal Pradeep Tambakhe
    Department of Computer science and Engineering                 19BE0463

                                                                                                                
                           
CONTENT
 Introduction 
 History
 Working
 Advantages
 Disadvantages
 Applications
 Future scope 
 Reference
INTRODUCTION

 Speech recognition is the process of converting an acoustic signal, captured


by a microphone or a telephone, to a set of words.

 Speech Recognition also known as automatic speech recognition or computer


speech recognition which means understanding voice by the computer and
performing required task
HISTORY

 The first speech recognition systems were focused on numbers, not words. In 1952, Bell Laboratories
designed the “Audrey” system which could recognize a single voice speaking digits aloud.
  Ten years later, IBM introduced “Shoebox” which understood and responded to 16 words in English.
 By the year 2001, speech recognition technology had achieved close to 80% accuracy. For most of the
decade there weren’t a lot of advancements until Google arrived with the launch of Google Voice
Search. Because it was an app, this put speech recognition into the hands of millions of people
 In 2011 Apple launched Siri which was similar to Google’s Voice Search. The early part of this decade
saw an explosion of other voice recognition apps. And with Amazon’s Alexa, Google Home we’ve
seen consumers becoming more and more comfortable talking to machines.
 Today, some of the largest tech companies are competing to herald the speech accuracy title. In
2016, IBM achieved a word error rate of 6.9 percent. In 2017 Microsoft usurped IBM with a 5.9
percent claim. Shortly after that IBM improved their rate to 5.5 percent. However, it is Google that
is claiming the lowest rate at 4.9 percent.
WORKING
 The first component of speech recognition is, of course, speech. Speech must be
converted from physical sound to an electrical signal with a microphone, and then to
digital data with an analog-to-digital converter. Once digitized, several models can be
used to transcribe the audio to text.
 Installing speech recogition : $ pip install SpeechRecognition
 Working with Microphone: To install PyAudio Package
image
ADVANTAGES

Voice recognition technology faster

Accuracy is fairly good

Hands-free focused work

Boosts Productivity level


DISADVANTAGES

 Automatic speed recognition software  doesn't understand the complexities of


the jargon
 Accuracy is not reliable
 Traning is needed
APPLICATION Amazon's Alexa
S
Apple Siri

Google's Google Assistant

Microsoft Cortana
FUTURE SCOPE

 Accuracy will become better


 Dictation speed recognition will gradually become accepted
 Small hard-held writing tablets for computer speech recognition dictation and data entry
will be develop,as faster pocessors and more memory become available
 Microphone and sound system will be desinged to adapt more quickly to changing
background noise levels, different environment, with better recognition of extraneous to be
discarded
REFERENCES

 "Speaker Independent Connected Speech Recognition- Fifth Generation Comp


uter Corporation"
. Fifthgen.com. Archivedfrom the original on 11 November 2013.
Retrieved 15 June 2013.
 ^ P. Nguyen (2010). "Automatic classification of speaker
characteristics". International Conference on Communications and Electronics
2010. pp. 147–152. doi:10.1109/ICCE.2010.5670700. ISBN 978-1-4244-7055-6. 
S2CID 13482115.
 ^ "British English definition of voice recognition". Macmillan Publishers
Limited. Archived from the original on 16 September 2011. Retrieved 21
February 2012.
 ^ "voice recognition, definition of". WebFinance, Inc. Archivedfrom the
original on 3 December 2011. Retrieved 21 February 2012.
                            THANK YOU!!!
   

You might also like