You are on page 1of 15

Speech Recognition

System
Contents
• Introduction
• Challenges of Speech Recognition
• Steps of Speech Recognition
• Required packages
• Use cases
• Advantages
• Disadvantages
• Conclusion

2
Introduction
What is the task?
• Getting a computer to understand spoken
language
• By “understand” we might mean
– React appropriately
– Convert the input speech into another
medium, e.g. text
• Several variables impinge on this (see later)

3
Introduction
How humans do it?

Articulation produces
sound waves which
the ear conveys to the brain
for processing
4
Introduction
How might computers do it?

Acoustic
Acoustic signal
waveform

• Digitization
• Acoustic analysis of the Speech
speech signal recognition
• Linguistic interpretation
5
Challenges

• Style of speaking
• Environment
• Speaker characteristics
• Task specifiers

6/34
Steps of Speech Recognition
• Digitization
– Converting analogue signal into digital representation
• Signal processing
– Separating speech from background noise
• Phonetics
– Variability in human speech
• Phonology
– Recognizing individual sound distinctions (similar phonemes)
• Lexicology and syntax
– Disambiguating homophones
– Features of continuous speech
• Syntax and pragmatics
– Interpreting prosodic features
• Pragmatics
– Filtering of performance errors (disfluencies)
7
Required Packages
• SpeechRecognition: The package has a Recognizer
class which is used to recognize the speech. Following
are seven methods which can read various audio
sources using different APIs.
• recognize_bing( )
• recognize_google( )
• recognize_google_cloud( )
• recognize_houndify( )
• recognize_ibm( )
• recognize_wit( )
• recognize_sphinx( )

8
Required Packages

• Pocketsphinx: recognize_sphinx API can be used to


run the speech recognition system offline as well. It
requires the installation of Pocketsphinx.
• PyAudio: To use the microphones, we will have to install
pyaudio module as well. We use the microphone class to
get the input speech from the microphone.

9
Sample Code
import speechrecognition as sr
r = sr.Recognizer() #instance of recognizer class
with sr.Microphone() as source:
audio = sr.listen(source) #listen to the voice
try:
get = r2.recognize_google(audio) #process the received audio
print(get) #print the received audio
except sr.UnknownValueError:
print('error’)

Output:
This program will show the input speech as a text output

10
Use Cases
• Search for documents on your computer.
• Print documents on request.
• Dictate the information you want to be
incorporated into a document.
• Set reminders with voice command.

11
Advantages
• Work processes become more efficient.
• Saves a great deal of labor.
• Improves efficiency, leads to more structured
work.
• Aiding the Visually- and Hearing-Impaired.
• Enabling Hands Free Technology.

12
Disadvantages
• Lack of Accuracy and Misinterpretation
• Accents and Speech Recognition
• Background Noise Interference
• Misused with pre-recorded verbal message
• Initial training cost high and poor productivity

13
Conclusion
At some point in future, speech recognition may become
speech understanding.
The statistical models that allow computers to decide what
a person just said may someday allow the to grasp the
meaning behind the words.
Although it is a huge leap in terms of computational power
and software sophistication, some researchers argue that
speech recognition development offers the most direct line
from the computers of today to true artificial intelligence.

14
Thank you

You might also like