Fast i-vector denoising using MAP estimation and a noise distributions database for robust speaker recognition

WB Kheder, D Matrouf, PM Bousquet… - Computer Speech & …, 2017‏ - Elsevier
Once the i-vector paradigm has been introduced in the field of speaker recognition, many
techniques have been proposed to deal with additive noise within this framework. Due to the …

A unified joint model to deal with nuisance variabilities in the i-vector space

WB Kheder, D Matrouf, M Ajili… - IEEE/ACM Transactions …, 2018‏ - ieeexplore.ieee.org
The past decade has witnessed a significant improvement in speaker recognition (SR)
technology in terms of performance with the introduction of the i-vectors framework. Despite …

Reliability of voice comparison for forensic applications

M Ajili - 2017‏ - hal.science
It is common to see voice recordings being presented as a forensic trace in court. Generally,
a forensic expert is asked to analyse both suspect and criminal's voice samples in order to …

A study of speech distortion conditions in real scenarios for speech processing applications

D Ribas, E Vincent, JR Calvo - 2016 IEEE Spoken Language …, 2016‏ - ieeexplore.ieee.org
The growing demand for robust speech processing applications able to operate in adverse
scenarios calls for new evaluation protocols and datasets beyond artificial laboratory …

Dealing with additive noise in speaker recognition systems based on i-vector approach

D Matrouf, WB Kheder, PM Bousquet… - 2015 23rd European …, 2015‏ - ieeexplore.ieee.org
In the last years, the i-vector approach became the state-of-the-art in speaker recognition
systems. As in previous approaches, i-vector-based systems suffer greatly in presence of …

[PDF][PDF] Probabilistic Approach Using Joint Clean and Noisy i-Vectors Modeling for Speaker Recognition.

WB Kheder, D Matrouf, M Ajili, JF Bonastre - Interspeech, 2016‏ - researchgate.net
Additive noise is one of the main challenges for automatic speaker recognition and several
compensation techniques have been proposed to deal with this problem. In this paper, we …

Domain mismatch modeling of out-domain i-vectors for PLDA speaker verification

MH Rahman, I Himawan, D Dean… - Proceedings of the 18th …, 2017‏ - eprints.qut.edu.au
The state-of-the-art i-vector based probabilistic linear discriminant analysis (PLDA) trained
on non-target (or out-domain) data significantly affects the speaker verification performance …

[PDF][PDF] Iterative Bayesian and MMSE-based noise compensation techniques for speaker recognition in the i-vector space.

WB Kheder, D Matrouf, M Ajili, JF Bonastre - Odyssey, 2016‏ - academia.edu
Dealing with additive noise in the i-vector space can be challenging due to the complexity of
its effect in that space. Several compensation techniques have been proposed in the last …

[PDF][PDF] Noise robust music artist recognition using i-vector

H Eghbal-Zadeh, G Widmer - 2016‏ - researchgate.net
In music information retrieval (MIR), dealing with different types of noise is important and the
MIR models are frequently used in noisy environments such as live performances. Recently …

Robust text independent closed set speaker identification systems and their evaluation

MTS Al-Kaltakchi - 2018‏ - theses.ncl.ac.uk
This thesis focuses upon text independent closed set speaker identi cation. The
contributions relate to evaluation studies in the presence of various types of noise and …