By Topic

Notice of Violation of IEEE Publication Principles
Speaker identification using Partially Connected Locally Recurrent Probabilistic Neural Networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Briciu, P.-M. ; Mil. Tehnical Acad., Bucharest, Romania

Notice of Violation of IEEE Publication Principles

"Speaker Identification using Partially Connected Locally Recurrent Probabilistic Neural Networks"
by P.M Briciu,
in the Proceedings of the 2010 8th International Conference on Communications, June 2010 pp.87-90

After careful and considered review of the content and authorship of this paper by an ad-hoc constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles.

Although the experiments are different, this paper contains theoretical portions of original text from the paper cited below. The original text was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without asking permission.

"Partially Connected Locally Recurrent Probabilistic Neural Networks",
by T. Ganchev K.E. Parsopoulos M.N. Vrahatis N. Fakotakis,
in Chapter 18 of Recurrent Neural Networks, September 2008, (Eds: X.-L. Hu and P.
Balasubramaniam), InTech, Vienna, Austria, pp.377-400

This paper introduces Partially Connected Locally Recurrent Probabilistic Neural Networks (PC-LRPNN) as an extension of the well-known Probabilistic Neural Networks (PNN) and Locally Recurrent Probabilistic Neural Networks (LRPNN). Besides the definition of the PC-LRPNN architecture a fast four-step training method is proposed. The first two steps are identical to the training of traditional PNNs, while the third and fourth steps adjusts the weights in the recurrent layer and selects the actual linkage that will be implemented in the recurrent layer. Finally, the superiority of PC-LRPNNs over PNNs on the task of speaker identification is demonstrated.

Published in:

Communications (COMM), 2010 8th International Conference on

Date of Conference:

10-12 June 2010