Sub-vector Extraction And Cascade Post-processing For Speaker Verification Using MLLR Super-vectors

Abstract

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 ap

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysarkar2016sub

Related papers

• Linear Regression For Speaker Verification (2018)0.00
• Improved Vocal Effort Transfer Vector Estimation For Vocal Effort-robust Speaker Verification (2023)0.00
• Investigation Of Using VAE For I-vector Speaker Verification (2017)0.00
• Multiobjective Optimization Training Of PLDA For Speaker Verification (2018)2.26
• A Unified Deep Learning Framework For Short-duration Speaker Verification In Adverse Environments (2020)9.41
• Coupling A Generative Model With A Discriminative Learning Framework For Speaker Verification (2021)5.24
• Label-efficient Self-supervised Speaker Verification With Information Maximization And Contrastive Learning (2022)6.77
• Improving Embedding Extraction For Speaker Verification With Ladder Network (2020)0.00