I-Vectors distance learning with Convolutional Neural Networks

From LRDE

Revision as of 17:05, 9 January 2018 by Bot (talk | contribs) (Created page with "{{CSIReport | authors = Valentin Iovene | title = I-Vectors distance learning with Convolutional Neural Networks | year = 2015 | number = 1903 | abstract = In this work we app...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Abstract

In this work we apply Convolutional Neural Networks to the task of speaker recognition. The CNN is used to approximate a measure of the distance between two i-vectors (representation of a speaker). Contrary to the commonly used cosine similarity measure, the function approximated by a CNN can be non-linear. The performance of this model will be compared to the ones of the Cosine Similarity measure and PLDA classification.