High-Level Speaker Verification via Articulatory-Feature based Sequence Kernels and SVM

Essay specific features

 

Issue:

Technology

 

Written by:

Rick D

 

Date added:

March 10, 2015

 

Level:

 

Grade:

A

 

No of pages / words:

11 / 2848

 

Was viewed:

5998 times

 

Rating of current essay:

 
Essay content:

Therefore, the method does not fully utilize the discriminative information available in the training data. To fully harness the discriminative information, this paper proposes training a support vector machine (SVM) for computing the verification scores. More precisely, the models of target speakers, individual background speakers, and claimants are converted to AF-supervectors, which form the inputs to an AF-based kernel of the SVM for computing verification scores...
displayed 300 characters

Custom written essay

All essays are written from scratch by professional writers according to your instructions and delivered to your email on time. Prices start from $11.99/page

Order custom paper

Full essays database

You get access to all the essays and can view as many of them as you like for as little as $28.95/month

Buy database access

Order custom writing paper now!

  • Your research paper is written
    by certified writers
  • Your requirements and targets are
    always met
  • You are able to control the progress
    of your writing assignment
  • You get a chance to become an
    excellent student!

Get a price guote

 
 

More precisely, the models of target speakers, individual background speakers, and claimants are converted to AF-supervectors, which form the inputs to an AF-based kernel of the SVM for computing verification scores. Results show that the proposed AF-kernel scoring is complementary to likelihood-ratio scoring, leading to better performance when the two scoring methods are combined...
displayed next 300 characters

General issues of this essay:

Related essays: