Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-End Speaker Verification

11/07/2018
by   Gautam Bhattacharya, et al.
0

This article presents a novel approach for learning domain-invariant speaker embeddings using Generative Adversarial Networks. The main idea is to confuse a domain discriminator so that is can't tell if embeddings are from the source or target domains. We train several GAN variants using our proposed framework and apply them to the speaker verification task. On the challenging NIST-SRE 2016 dataset, we are able to match the performance of a strong baseline x-vector system. In contrast to the the baseline systems which are dependent on dimensionality reduction (LDA) and an external classifier (PLDA), our proposed speaker embeddings can be scored using simple cosine distance. This is achieved by optimizing our models end-to-end, using an angular margin loss function. Furthermore, we are able to significantly boost verification performance by averaging our different GAN models at the score level, achieving a relative improvement of 7.2

READ FULL TEXT
research
11/07/2018

Adapting End-to-End Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training

In this article we propose a novel approach for adapting speaker embeddi...
research
08/11/2020

Neural PLDA Modeling for End-to-End Speaker Verification

While deep learning models have made significant advances in supervised ...
research
04/07/2021

Adapting Speaker Embeddings for Speaker Diarisation

The goal of this paper is to adapt speaker embeddings for solving the pr...
research
01/25/2021

Domain-Dependent Speaker Diarization for the Third DIHARD Challenge

This report presents the system developed by the ABSP Laboratory team fo...
research
10/07/2021

Disentangled dimensionality reduction for noise-robust speaker diarisation

The objective of this work is to train noise-robust speaker embeddings f...
research
07/19/2020

Meta-learning with Latent Space Clustering in Generative Adversarial Network for Speaker Diarization

The performance of most speaker diarization systems with x-vector embedd...
research
10/25/2019

Channel adversarial training for speaker verification and diarization

Previous work has encouraged domain-invariance in deep speaker embedding...

Please sign up or login with your details

Forgot password? Click here to reset