Add Papers Marked0
Paper checked off!

Marked works


Viewed works

Shopping Cart0
Paper added to shopping cart!

Shopping Cart

Register Now

internet library library

Great deal: today with a discount!

Regular price:
You save:
0,32 (13%)
Discounted price*:
Add to Wish List
ID number:752732
Published: 08.05.2003.
Language: English
Level: Secondary school
Literature: n/a
References: Not used

These two phrases are surprisingly similar when broken down into phonemes, yet have very different meanings. A program using a Markov Model at the sentence level might be able to ascertain which of these two phrases the speaker was actually using through statistical analysis using the phrase that preceded it. When the computer checks its Markov Model it would find that the first phrases is much more likely to appear than the second, so it uses as a base for the rest of the sentence. Yet, if the phrases where these sentences:
James's school drives monkey feet
James is cool because he plays the guitar
It would switch over to the second sentence, because the first sentence quickly turned meaningless, while the second was both semantically and syntactically correct. This sort of "understanding" is imperative for a speech recognition engine, and especially one that has to deal with continuous speech.

Author's comment
Load more similar papers

Send to email

Your name:

Enter an email address where the link will be sent:

{Your name} suggests you to check out this paper on „Speech Recognition”.

Link to paper:


Email has been sent

Choose Authorization Method

Email & Password

Email & Password

Wrong e-mail adress or password!
Log In

Forgot your password?


Not registered yet?

Register and redeem free papers!

To receive free papers from it is necessary to register. It's quick and will only take a few seconds.

If you have already registered, simply to access the free content.

Cancel Register