Variance-Spectra based Normalization for I-vector Standard and Probabilistic Linear Discriminant Analysis

Abstract : I-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) has become the state-of-the-art configuration for speaker verification. Recently, Gaussian-PLDA has been improved by a preliminary length normalization of i-vectors. This normalization, known to increase the Gaussianity of the i-vector distribution, also improves performance of systems based on standard Linear Discriminant Analysis (LDA) and "two-covariance model" scoring. But this technique follows a standardization of the i-vectors (centering and whitening i-vectors based on the first and second order moments of the development data). We propose in this paper two techniques of normalization based on total, between-and within-speaker variance spectra 1. These "spectral" techniques both normalize the i-vectors length for Gaussianity, but the first adapts the i-vectors representation to a speaker recognition system based on LDA and two-covariance scoring when the second adapts it to a Gaussian-PLDA model. Significant performance improvements are demonstrated on the male and female telephone portion of NIST SRE 2010.
Document type :
Conference papers
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01927751
Contributor : Anthony Larcher <>
Submitted on : Tuesday, November 20, 2018 - 10:04:36 AM
Last modification on : Tuesday, July 2, 2019 - 5:38:02 PM

File

paperSpectralNormV6.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01927751, version 1

Collections

Citation

Pierre-Michel Bousquet, Anthony Larcher, Driss Matrouf, Jean-François Bonastre, Oldřich Plchot. Variance-Spectra based Normalization for I-vector Standard and Probabilistic Linear Discriminant Analysis. Speaker Odyssey, Jun 2012, Singapour, Singapore. ⟨hal-01927751⟩

Share

Metrics

Record views

28

Files downloads

35