Speech Recognition

spectacularscarecrowAI and Robotics

Nov 17, 2013 (3 years and 8 months ago)

71 views

1

Speech Recognition

2

Introduction


What is Speech Recognition?


-

Voice Recognition?


Where can it be used?


-

Dictation


-

System control/navigation


-

Commercial/Industrial applications


-

Hand held digital recorders

3

Contents:


Continuous/Discrete


How does it work?


Recent improvements


Current software options


Future of SR

4

Continuous or Discrete?


Continuous speech


-

dictation


Discrete speech


-

system controls

5

How does SR work?


Recognition


Training


Correction


Command/Control

6

Recognition (1)

Voice Input

Analog to Digital

Acoustic Model

Language Model

Display

Speech Engine

Feedback

7

Recognition (2)

Acoustic Modeling


Spoken words: “I think there are…..”


Phonemes: ‘ ay th
-
in
-
nk
-
kd dh
-
eh
-
r aa
-
r’


H.M.M.’s: 5 state representation


Speech Engine


8

Recognition (3)

Language Modeling


Word context


Word frequency


Transition possibilities


9


Voice Training (1)

Can be done by:


Predetermined text segments


Individual words

Compare new acoustic with old and combines


More training = better recognition

10

Voice Training (2)

User specific Voice file


Voice qualities


Pronunciation


Patterns of word use


Preferred vocabulary




11


Making Corrections


Move cursor by voice command


Memorize edit commands


List of possible alternatives


Make correction manually


12

Command/Control


Desktop grid


Program or Link name/number


URL name


Memorized commands


13

Recent Improvements in SR


Faster training ~10 min.


Better recognition ~95%


More compatible software


Better system control/command

14

Current Software Options for PC


Dragon Systems


Naturally Speaking


Philips


FreeSpeech


IBM


ViaVoice


Lernout & Hauspie


Voice Xpress

15

How well do the work?

Training

Dictation
Correct.

App.

Integrat.

Command

-

Control

Dragon

Excellent

Excellent

Good

Good

Philips

Fair

Fair

Good

Good

IBM

Excellent

Good

Good

Excellent

L & H

Good

Good

Good

Good

16

Future of SR


SUI


Speech
-
based User Interface


Improvements needed:


-

Greater accuracy


-

Greater system control/command


-

More compatible software

17

Conclusion


SR Uses


How does it work?


Current Software


Problems of SR


More SR coming soon….

18

References


1. Alwang, Greg. “Speech Recognition,” PC Magazine, December 1
1999


2. Hauptmann, Alexander G. Jang, Photina Jaeyun. Carnegie Mellon
University. “Learning to Recognize Speech by Watching Television,”
IEEE Intelligent Systems, September/October 1999.


3. Miastkowski, Stan. “Latest Speech Software Gets You Up and
Running Faster,” PC World, November 1999.