O Ghahabi, J Hernando - IEEE/ACM Transactions on Audio …, 2017 - ieeexplore.ieee.org
The lack of labeled background data makes a big performance gap between cosine and Probabilistic Linear Discriminant Analysis (PLDA) scoring baseline techniques for i-vectors …
P Verma, PK Das - International Journal of Speech Technology, 2015 - Springer
In the domain of speech recognition many methods have been proposed over time like Gaussian mixture models (GMM), GMM with universal background model (GMM-UBM …
O Ghahabi, J Hernando - 2015 IEEE International Conference …, 2015 - ieeexplore.ieee.org
The use of Restricted Boltzmann Machines (RBM) is proposed in this paper as a non-linear transformation of GMM supervectors for speaker recognition. It will be shown that the RBM …
In this paper, we propose to discriminatively model target and impostor spectral features using Deep Belief Networks (DBNs) for speaker recognition. In the feature level, the number …
Restricted Boltzmann Machines (RBMs) have shown success in different stages of speaker recognition systems. In this paper, we propose a novel framework to produce a vector-based …
K Kiani, A Baniasadi - 2019 5th Iranian Conference on Signal …, 2019 - ieeexplore.ieee.org
The process of manually labeling data is not affordable. Moreover, the lack of labeled data has led to a big performance gap between scoring baseline techniques in speaker …
It is supposed in Speaker Recognition (SR) that everyone has a unique voice which could be used as an identity rather than or in addition to other identities such as fingerprint, face, or …
This thesis is about a research conducted in the area of Speaker Recognition. The application is concerned to the automatic detection and tracking of target speakers in …
Restricted Boltzmann Machines (RBMs) have shown success in speaker recognition. In this paper, RBMs are investigated in a framework comprising a universal model training and …