R
Réda Dehak
Researcher at École Pour l'Informatique et les Techniques Avancées
Publications - 25
Citations - 5427
Réda Dehak is an academic researcher from École Pour l'Informatique et les Techniques Avancées. The author has contributed to research in topics: Speaker recognition & Support vector machine. The author has an hindex of 15, co-authored 22 publications receiving 4734 citations. Previous affiliations of Réda Dehak include Massachusetts Institute of Technology & École Normale Supérieure.
Papers
More filters
Journal ArticleDOI
Front-End Factor Analysis for Speaker Verification
TL;DR: An extension of the previous work which proposes a new speaker representation for speaker verification, a new low-dimensional speaker- and channel-dependent space is defined using a simple factor analysis, named the total variability space because it models both speaker and channel variabilities.
Proceedings ArticleDOI
Language Recognition via i-vectors and Dimensionality Reduction.
TL;DR: In this paper, a new language identification system is presented based on the total variability approach previously developed in the field of speaker identification and various techniques are employed to extract the most salient features in the lower dimensional i-vector space.
Proceedings Article
Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification
TL;DR: A new speaker verification system architecture based on Joint Factor Analysis (JFA) as feature extractor is presented, using the use of the cosine kernel in the new total factor space to design two different systems: the first system is Support Vector Machines based, and the second one uses directly this kernel as a decision score.
Cosine Similarity Scoring without Score Normalization Techniques.
TL;DR: This paper introduces a modification to the cosine similarity that does not require explicit score normalization, relying instead on simple mean and covariance statistics from a collection of impostor speaker ivectors to enable application of a new unsupervised speaker adaptation technique to models defined in the ivector space.
Journal ArticleDOI
Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach
TL;DR: An improved clustering method is integrated with an existing re-segmentation algorithm and an iterative optimization scheme is implemented that demonstrates the ability to improve both speaker cluster assignments and segmentation boundaries in an unsupervised manner.