ADDITIVE NOISE COMPENSATION IN THE I-VECTOR SPACE FOR SPEAKER RECOGNITION

Abstract : State-of-the-art speaker recognition systems performance degrades considerably in noisy environments even though they achieve very good results in clean conditions. In order to deal with this strong limitation, we aim in this work to remove the noisy part of an i-vector directly in the i-vector space. Our approach offers the advantage to operate only at the i-vector extraction level, letting the other steps of the system unchanged. A maximum a posteriori (MAP) procedure is applied in order to obtain clean version of the noisy i-vectors taking advantage of prior knowledge about clean i-vectors distribution. To perform this MAP estimation, Gaussian assumptions over clean and noise i-vectors distributions are made. Operating on NIST 2008 data, we show a relative improvement up to 60% compared with baseline system. Our approach also out-performs the "multi-style" backend training technique. The efficiency of the proposed method is obtained at the price of relative high computational cost. We present at the end some ideas to improve this aspect.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02157205
Contributor : Jean-François Bonastre <>
Submitted on : Saturday, June 15, 2019 - 5:01:20 PM
Last modification on : Tuesday, July 2, 2019 - 5:38:02 PM

File

waad_benkheder_icassp2015.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02157205, version 1

Collections

Citation

Waad Kheder, Driss Matrouf, Jean-François Bonastre, Moez Ajili, Pierre-Michel Bousquet. ADDITIVE NOISE COMPENSATION IN THE I-VECTOR SPACE FOR SPEAKER RECOGNITION. ICASSP, 2015, South Brisbane, Australia. ⟨hal-02157205⟩

Share

Metrics

Record views

6

Files downloads

14