The document outlines a speech recognition project developed by a team of students from the Department of CSE. The project aims to reduce language barriers using speech recognition technology. The team includes N.Sateesh, K.Madan, P.Gowtham, and P.Hemakrishna, guided by Mr. B. Hari Babu. The project uses machine learning for speech recognition and includes modules for installation of required libraries and packages. The document discusses the working process, advantages like accuracy and speed, and disadvantages such as imperfect accuracy and inability to understand complex language.

1. Department of CSE
Team Members:
N.Sateesh :19G21A05B1
K.Madan :19G21A0574
P.Gowtham :19G21A05B4
P.Hemakrishna :19G21A05D4
Guided By:
Mr.B.Hari Babu
Assistant Professor
Project Title:
Speech Recognition
using Machine
Learning

2. Department of CSE
R
U
U
Outline:
➢Abstract
➢Introduction
➢Working process
➢Modules
➢Advantages and Disadvantages
➢Conclusion

3. Department of CSE
Abstract
✓ Speech recognition is one of the fastest-growing engineering
technologies.
✓ It has several applications in different areas, and provides many
potential benefits.
✓ A lot of people are unable to communicate due to language
barriers.

4. Department of CSE
✓ We aim to reduce this barrier via our project, which was
designed and developed to achieve systems in particular cases to
provide significant help so people can share information by
operating a computer using voice input.

5. Department of CSE
Introduction
✓ In this project we are trying to reduce the language barriers
among people .
✓ Speech recognition is also used in call center applications
and mobile wireless communication.

6. Department of CSE
✓ The method of converting an acoustic signal, captured by a
microphone or other instrument, into a set of words is
speech recognition.
✓ A speech synthesizer converts written text into spoken
language. Speech synthesis is also referred to as text-to-
speech (TTS) conversion

7. Department of CSE
Working process

8. Department of CSE
Modules
✓Pip install pipwin
✓Pipwin install pyaudio
✓Pip install speechRecognition

9. Department of CSE
Adavantages
✓ It is fairly accurate.
✓ It allows for hand free work.
✓ It is faster.

10. Department of CSE
Disadvantages
✓Accuracy is always imperfect.
✓The software cannot understand complexities of jargon
or phrasing.
✓Some voices don’t come across well.

11. Department of CSE
Conclusion
✓In the past few years, the complexity and precision of
speech recognition applications have evolved exponentially.
✓This paper extensively explores the recent advancements in
intelligent vision and speech algorithms, their applications
on the most popular smart phones and embedded platforms,
and their application limitations.

12. Thank you