Ch0-Introduction

Ch0-Introduction - ECE5527 Speech Recognition Introduction...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
ECE-5527 Speech Recognition Introduction to Automatic Speech Recognition
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 2 Introduction to Speech Recognition Introduction to ASR Problem definition State of the art examples Course overview Lecture outline Assignments Term Project Grading
Background image of page 2
INTRODUCTION TO AUTOMATIC SPEECH RECOGNTION February 13, 2012 Veton Këpuska 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 4 Communication via Spoken Language   Speech Speech Input Output Text Text Meaning Understanding Generation Human Computer
Background image of page 4
February 13, 2012 Veton Këpuska 5 Automatic Speech Recognition Spoken language understanding is a difficult task, and it is  remarkable that humans do well at it.  The goal of  automatic speech recognition  ASR ( ASR research is to address this problem computationally by building  systems that map from an acoustic signal to a string of words.  Automatic speech understanding  ( ASU ) extends this goal to  producing some sort of understanding of the sentence, rather  than just the words.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 6 Virtues of Spoken Language Natural:       Requires no special training Flexible:       Leaves hands and eyes free Efficient:       Has high data rate Economical:    Can be transmitted/received inexpensively Speech interfaces are ideal for information access and  management when: • The information space is broad and complex, • The users are technically naive, or • Only telephones are available Speech interfaces are ideal for information access and  management when: • The information space is broad and complex, • The users are technically naive, or • Only telephones are available
Background image of page 6
February 13, 2012 Veton Këpuska 7 Application Areas The general problem of  automatic transcription of speech  by  any speaker in any environment is still far from solved. But  recent years have seen ASR technology mature to the point  where it is viable in certain limited domains.  One major application area is in  human-computer interaction While many tasks are better solved with visual or pointing  interfaces, speech has the potential to be a better interface  than the keyboard for tasks where full natural language  communication is useful, or for which keyboards are not  appropriate.  This includes hands-busy or eyes-busy applications, such as  where the user has objects to manipulate or equipment to  control. 
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
February 13, 2012 Veton Këpuska 8 Application Areas Another important application area is  telephony , where speech  recognition is already used for example  in spoken dialogue systems for entering digits, recognizing  “yes” to accept collect calls, 
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 34

Ch0-Introduction - ECE5527 Speech Recognition Introduction...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online