TY  - JOUR
T1  - Unsupervised Speaker Retrieval and Identification in Large Scale Environment
AU - Ammar, Rami AU - Jaffar, Assef AU - Aljoumaa, Kadan 
JO  - Journal of Engineering and Applied Sciences
VL  - 15
IS  - 11
SP  - 2457
EP  - 2463
PY  - 2020
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2020.2457.2463
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2020.2457.2463
KW  - I-Vector technique
KW  -speaker identification
KW  -k-means++
KW  -large-scale environment
KW  -deep autoencoder
KW  -SideKit
KW  -VoxCeleb
AB  - The identity vector is one of the state-of-the-art
techniques for building speaker identification and retrieval
systems. These systems are used in many crucial
applications. Recently, mainly due to the facilities in
audio content acquisition, the need to analyzing unlabeled
datasets has become a vital advantage. Our contribution
is to enhance the identity vector approach by using
k-means++ instead of using the random initial state of the
universal background model “UBM”, this randomness
may lead to a local minimum. This enhancement
increased the accuracy of the system and decreased the
needed number of epochs, thus, decreased the training
time. In addition, we presented a study of the effect of
changing the voice information extraction and the UBM
parameters also we enhanced the performance of the
system by using dimensionality reduction for identity
vectors through using a deep autoencoder. Finally, we
enhanced the well-known “SideKit” toolkit to work on
large datasets in batches. We used a large dataset obtained
under different conditions “VoxCeleb1”. VoxCeleb1 is a
free and well-known dataset was recorded in real-world
conditions.
ER  -