Scribd
Upload
33 views

Automatic Speech

This document discusses automatic speech recognition. It begins by imagining a scenario where a man without hands can access the internet as quickly as someone using a computer. It then provides an introduction, explaining that automatic speech recognition is a system that derives words from acoustic speech. It describes the working of speech recognition through speech to data conversion and statistical modeling using hidden Markov models. It lists applications such as improving electronic medical records in healthcare and voice control in high performance aircraft. Weaknesses include low signal-to-noise ratio, overlapping speech, and high computer power usage. Further applications are discussed in areas like court reporting, hands-free computing, home automation, and robotics. The conclusion states that with high recognition accuracy, applications of this technology

Uploaded by

Srikanth Durgam
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
33 views

Automatic Speech

This document discusses automatic speech recognition. It begins by imagining a scenario where a man without hands can access the internet as quickly as someone using a computer. It then provides an introduction, explaining that automatic speech recognition is a system that derives words from acoustic speech. It describes the working of speech recognition through speech to data conversion and statistical modeling using hidden Markov models. It lists applications such as improving electronic medical records in healthcare and voice control in high performance aircraft. Weaknesses include low signal-to-noise ratio, overlapping speech, and high computer power usage. Further applications are discussed in areas like court reporting, hands-free computing, home automation, and robotics. The conclusion states that with high recognition accuracy, applications of this technology

Uploaded by

Srikanth Durgam
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

AUTOMATIC SPEECH RECOGNITION

G.ADITHYA SHANKER

D.BHAVANI

B.Tech Second year SSJ ENGINEERING COLLEGE HYDERABAD

CONTENTS
INTRODUCTION WORKING APPLICATIONS WEAKNESS FURTHER APPLICATIONS CONCLUSION

IMAGINE!!

A man with no hands accessing internet as an ordinary man or even faster than a computer expert!!

IS THIS POSSIBLE??

Does it sound fantasy or is it real??

It can be made possible by AUTOMATIC SPEECH RECOGNITION.

INTRODUCTION

What is Speech Recognition System? It is an automated phone system. Why is it used? To derive a sequence of words from a stream of acoustic information.

Its Components: 1. Language Understanding 2. Language Generation 3. Speech Synthesis Classification: 1. Small vocabulary/ Many users 2. Large vocabulary/limited users

WORKING

Speech to Data conversion

Speech Recognition and Statistical Modeling Hidden Markov model

APPLICATIONS
Health care Electronic Medical Records applications can be more effective. Military High Performance fighter air craft. Disabled people Useful for people who are unable to use their hands.

WEAKNESS

Low signal-to-noise ratio Overlapping Speech Intensive use of computer power

Homonyms eg:- bee,be there,their air,heir

FURTHER APPLICATIONS
Court Reporting Hands free computing Home Automation Medical Transcriptions Robotics Pronunciation evaluation

CONCLUSION

With high recognition accuracy its applications can be varied over wide range.

ANY QUERIES ? ? ??

THANK YOU

You might also like