DMDriss Matrouf

Driss Matrouf

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Driss Matrouf has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

    • 26 February 2024
    • Published by HAL in HAL
    Open Access

    Learning linguistic content embeddings for phrase and language independent utterance verification

    by Mohammad Mohammadamini, Nathan Griot, Driss Matrouf

    In this paper, we introduce a phrase and language-independent utterance verification system. The objective of an utterance verification system is to confirm whether the linguistic content of two speech utterances is the same or not. Our proposed approach is phrase and language-independent, therefore it can generalize for unseen phrases and even unseen languages. The proposed framework is based on a ResNet embedding extractor trained on the Common Voice dataset which is optimized by a linguistic content classification task.The proposed approach can be used in text-dependent speaker recognition systems, passphrase verification systems, and keyword spotting systems. Our system is tested on several protocols including Deepmine for text-dependent speaker verification and Speech Commands' keyword-spotting benchmarks. Obtaining high performance for unseen phrases and languages makes our approach plausible for utterance verification in low-resource and even zero-resource languages. For example, the EER for a protocol on Common Voice English is 0.16 while for Common Voices French without using French training data the EER is 1.23.

  • A Unified Joint Model to Deal With Nuisance Variabilities in the i-Vector Space

    by Waad Ben Kheder, Driss Matrouf, Moez Ajili, Jean-Francois Bonastre

    The past decade has witnessed a significant improvement in speaker recognition technology (SR) in terms of performance with the introduction of the i-vectors framework. Despite these advances, the performance of SR systems considerably suffers in presence of acoustic nuisances and variabilities. In this paper, we develop a data driven nuisance compensation technique in the i-vector space without referring to the effects of the targeted nuisances in the temporal domain. This approach is non-parametric as it does not suppose a specific relationship between a “good” version of an i-vector and its corrupted version. Instead, our algorithm models directly the joint distribution of both representations (the good i-vector and its corrupted version) and takes advantage of the reproducibility of acoustic corruptions to generate the corrupted i-vectors. We then build an MMSE estimator that computes an improved version of a corrupted test i-vector given this joint distribution. Experiments are carried out on NIST SRE 2010 and SITW (Speakers In The Wild) databases where the proposed algorithm is used to deal with additive noise and short utterances. Our technique is shown to be efficient, improving the baseline system performance in terms of EER by up to 70% when used on known test noises and up to 65% in the context of unseen noises using a generic model. It was also proven efficient in the context of duration mismatch reaching up to 40% of relative improvement when used on short utterances using multiple models corresponding to different durations and up to 36% when used on arbitrary duration test segments.


  • Open Access

    Sub-vector Extraction and Cascade Post-Processing for Speaker Verification Using MLLR Super-vectors

    by A. K. Sarkar, C. Barras, V. B. Le, D. Matrouf

    In this paper, we propose a speaker-verification system based on maximum likelihood linear regression (MLLR) super-vectors, for which speakers are characterized by m-vectors. These vectors are obtained by a uniform segmentation of the speaker MLLR super-vector using an overlapped sliding window. We consider three approaches for MLLR transformation, based on the conventional $1$-best automatic transcription, on the lattice word transcription, or on a simple global universal background model (UBM). Session variability compensation is performed in a post-processing module with probabilistic linear discriminant analysis (PLDA) or the eigen factor radial (EFR). Alternatively, we propose a cascade post-processing for the MLLR super-vector based speaker-verification system. In this case, the m-vectors or MLLR super-vectors are first projected onto a lower-dimensional vector space generated by linear discriminant analysis (LDA). Next, PLDA session variability compensation and scoring is applied to the reduced-dimensional vectors. This approach combines the advantages of both techniques and makes the estimation of PLDA parameters easier. Experimental results on telephone conversations of the NIST 2008 and 2010 speaker recognition evaluation (SRE) indicate that the proposed m-vector system performs significantly better than the conventional system based on the full MLLR super-vectors. Cascade post-processing further reduces the error rate in all cases. Finally, we present the results of fusion with a standard i-vector system in the feature, as well as in the score domain, demonstrating that the m-vector system is both competitive and complementary with it.

  • Integration of Word and Semantic Features for Theme Identification in Telephone Conversations

    by Yannick Estève, Mohamed Bouallegue, Carole Lailler, Mohamed Morchid, Richard Dufour, Georges Linarès, Driss Matrouf, Renato De Mori


  • Modeling nuisance variabilities with factor analysis for GMM-based audio pattern classification

    by Driss Matrouf, Florian Verdet, Mickaël Rouvier, Jean-François Bonastre, Georges Linarès


  • Transfer Function-Based Voice Transformation for Speaker Recognition

    by Jean-Francois Bonastre, Driss Matrouf, Corinne Fredouille

    This paper investigates the effect of a transfer function-based voice transformation on automatic speaker recognition system performance. We focus on increasing the impostor acceptance rate, by modifying the voice of an impostor in order to target a specific speaker. This paper is based on the following idea: in several applications and particularly in forensic situations, it is reasonable to think that some organizations have a knowledge on the speaker recognition method used and could impersonate a given, well known speaker. We also evaluate the effect of the voice transformation when the transformation is applied both on client and impostor trials. This paper presents some experiments based on NIST SRE 2005 protocol. The results show that the voice transformation allows a drastic increase of the false acceptance rate, without damaging the natural aspect of the voice. It seems also that this kind of voice transformation could be efficient for reducing the inter-session mismatch


  • Accurate Log-Likelihood Ratio Estimation by using Test Statistical Model for Speaker Verification

    by Driss Matrouf, Jean-Francois Bonastre

    In this paper we propose an accurate estimation of the log-likelihood ratio (LLR) thanks to a statistical modelling of the test data. This work takes place within the framework of GMM/UBM based speaker verification. Modelling the test data using a statistical model like a GMM shows several advantages, and particularly it allows to reduce the influence of out-of-domain data thanks to the underlined statistical model. In this paper, we explore the interests of such methods, using a GMM modelling of the test data. We propose also an extension of this approach to the MAP-based speaker model adaptation. Some experiments based on the NIST SRE 2005 protocol are presented and show a significant gain (between 4% and 5% in relative compared to our NIST GMM/UBM baseline) by using our LLR estimation