Umair Khan

Mr. Umair Khan

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 July 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
UKUmair Khan
Umair Khan
PSpooyan safari
pooyan safari
Javier HernandoJavier Hernando
Javier Hernando
Restricted Boltzmann Machines (RBMs) have shown success in both the front-end and backend of speaker verification systems. In this paper, we propose applying RBMs to the front-end for the tasks of speaker clustering and speaker tracking in TV broadcast shows. RBMs are trained to transform utterances into a vector based representation. Because of the lack of data for a test speaker, we propose RBM adaptation to a global model. First, the global model—which is referred to as universal RBM—is trained with all the available background data. Then an adapted RBM model is trained with the data of each test speaker. The visible to hidden weight matrices of the adapted models are concatenated along with the bias vectors and are whitened to generate the vector representation of speakers. These vectors, referred to as RBM vectors, were shown to preserve speaker-specific information and are used in the tasks of speaker clustering and speaker tracking. The evaluation was performed on the audio recordings of Catalan TV Broadcast shows. The experimental results show that our proposed speaker clustering system gained up to 12% relative improvement, in terms of Equal Impurity (EI), over the baseline system. On the other hand, in the task of speaker tracking, our system has a relative improvement of 11% and 7% compared to the baseline system using cosine and Probabilistic Linear Discriminant Analysis (PLDA) scoring, respectively.

3 August 2022 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
UKUmair Khan
Umair Khan
Muazzam MaqsoodMuazzam Maqsood
Muazzam Maqsood
SGSaira Gillani
Saira Gillani
MDMehr Yahya Durrani
Mehr Yahya Durrani
IMIrfan Mehmood
Irfan Mehmood
Sanghyun SeoSanghyun Seo
Sanghyun Seo

1 September 2019
Verified
Conference Paper
Closed access
UKUmair Khan
Umair Khan
JHJavier Hernando
Javier Hernando

15 September 2019
Verified
Conference Paper
Open access
UKUmair Khan
Umair Khan
MIMiquel India
Miquel India
JHJavier Hernando
Javier Hernando

27 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
UKUmair Khan
Umair Khan
Javier HernandoJavier Hernando
Javier Hernando
This report describes the submission from Technical University of Catalonia (UPC) to the VoxCeleb Speaker Recognition Challenge (VoxSRC-20) at Interspeech 2020. The final submission is a combination of three systems. System-1 is an autoencoder based approach which tries to reconstruct similar i-vectors, whereas System-2 and -3 are Convolutional Neural Network (CNN) based siamese architectures. The siamese networks have two and three branches, respectively, where each branch is a CNN encoder. The double-branch siamese performs binary classification using cross entropy loss during training. Whereas, our triple-branch siamese is trained to learn speaker embeddings using triplet loss. We provide results of our systems on VoxCeleb-1 test, VoxSRC-20 validation and test sets.