Skip to Main content Skip to Navigation
Conference papers

Denoising x-vectors for Robust Speaker Recognition

Abstract : Using deep learning methods has led to significant improvement in speaker recognition systems. Introducing x-vectors as a speaker modeling method has made these systems more robust. Since, in challenging environments with noise and reverberation, the performance of x-vectors systems degrades significantly, the demand for denoising techniques remains as before. In this paper, for the first time, we try to denoise the x-vectors speaker embedding. Our focus is on additive noise. Firstly, we use the i-MAP method which considers that both noise and clean x-vectors have a Gaussian distribution. Then, leveraging denoising autoencoders (DAE) we try to reconstruct the clean x-vector from the corrupted version. After that, we propose two hybrid systems composed of statistical i-MAP and DAE. Finally, we propose a novel DAE architecture, named Deep Stacked DAE, composed of several DAEs where each DAE receives as input the output of its predecessor DAE concatenated with the difference between noisy x-vectors and its predecessor's output. The experiments on Fabiol corpus show that the results given by the hybrid DAE i-MAP method in several cases outperforms the conventional DAE and i-MAP methods. Also, the results for Deep Stacked DAE in most cases is better than the other proposed methods. For utterances longer than 12 seconds we achieved a 51% improvement in terms of EER with Deep Stacked DAE, and for utterances shorter than 2 seconds, Deep Stacked DAE gives 18% improvements compared to the baseline system.
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02614616
Contributor : Mohammad Mohammadamini <>
Submitted on : Thursday, May 21, 2020 - 12:00:11 PM
Last modification on : Tuesday, June 16, 2020 - 9:25:26 AM

File

78 (1).pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Mohammad Mohammadamini, Driss Matrouf, Paul-Gauthier Noé. Denoising x-vectors for Robust Speaker Recognition. Odyssey 2020 The Speaker and Language Recognition Workshop, Nov 2020, Tokyo, Japan. pp.75-80, ⟨10.21437/Odyssey.2020-11⟩. ⟨hal-02614616⟩

Share

Metrics

Record views

172

Files downloads

35