Viet Bac Le
Viet Bac Le has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Claude Barras
LIMSI/CNRS, Université Paris-Sud
3 shared publications - Anindya Roy
LIMSI/CNRS
2 shared publications - Hervé Bredin
LIMSI CNRS Univ. Paris-Sud Université Paris-Saclay Orsay France
2 shared publications - A. K. Sarkar1 shared publication
- Driss Matrouf
LIA, Université d'Avignon, Agroparc, BP 1228, 84911 Avignon CEDEX 9, France
1 shared publication - Jean-Luc Gauvain
Spoken Language Processing Group, LIMSI-CNRS
1 shared publication
Latest Publications
- Open Access
Sub-vector Extraction and Cascade Post-Processing for Speaker Verification Using MLLR Super-vectors
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.
Open AccessSub-vector Extraction and Cascade Post-Processing for Speaker Verification Using MLLR Super-vectors
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.
- 17 April 2014
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 74 (4) , 1377-1396
Lexical speaker identification in TV shows
- 17 April 2014
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 74 (4) , 1377-1396
Lexical speaker identification in TV shows