SPEAKER VERIFICATION USING M-VECTOR EXTRACTED FROM MLLR SUPER-VECTOR

Abstract : In this paper, we propose a speaker verification system called m-vector system, where speakers are represented by uniform segmen-tation of their Maximum Likelihood Linear Regression (MLLR) super-vectors, denoted m-vectors. The MLLR super-vectors are extracted with respect to Universal Background Model (UBM) with MLLR adaptation using the speakers data. Two criterion are followed to segment the MLLR super-vector: one is disjoint segmen-tation technique and other one is overlapped windows. Afterward, m-vectors are conditioned by our recently proposed [1] session variability compensation algorithm before calculating score during test phase. However, the proposed method is not based on any total variability space concept and uses simple MLLR transformation for extracting m-vector without considering any transcription of the speech segment. The proposed system shows promising performance compared to the conventional i-vector system. This indicates that session variability compensation plays an important role in speaker verification. Speakers can be represented by simpler way instead of generating i-vector in conventional system and able to achieve performance comparable to the i-vector based system. Experiment results are shown on NIST 2008 SRE core condition.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01320317
Contributor : Bibliothèque Universitaire Déposants Hal-Avignon <>
Submitted on : Monday, May 23, 2016 - 4:28:09 PM
Last modification on : Tuesday, July 2, 2019 - 5:38:02 PM

Identifiers

  • HAL Id : hal-01320317, version 1

Collections

Citation

A. Sarkar, Jean-François Bonastre, Driss Matrouf. SPEAKER VERIFICATION USING M-VECTOR EXTRACTED FROM MLLR SUPER-VECTOR. EUSIPCO 20th European Signal Processing Conference, Aug 2012, Bucarest, Romania. ⟨hal-01320317⟩

Share

Metrics

Record views

34