DeepAI
Log In Sign Up

The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification

10/21/2020
by   Jenthe Thienpondt, et al.
0

In this paper we propose and analyse a large margin fine-tuning strategy and a quality-aware score calibration in text-independent speaker verification. Large margin fine-tuning is a secondary training stage for DNN based speaker verification systems trained with margin-based loss functions. It enables the network to create more robust speaker embeddings by enabling the use of longer training utterances in combination with a more aggressive margin penalty. Score calibration is a common practice in speaker verification systems to map output scores to well-calibrated log-likelihood-ratios, which can be converted to interpretable probabilities. By including quality features in the calibration system, the decision thresholds of the evaluation metrics become quality-dependent and more consistent across varying trial conditions. Applying both enhancements on the ECAPA-TDNN architecture leads to state-of-the-art results on all publicly available VoxCeleb1 test sets and contributed to our winning submissions in the supervised verification tracks of the VoxCeleb Speaker Recognition Challenge 2020.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/23/2020

The IDLAB VoxCeleb Speaker Recognition Challenge 2020 System Description

In this technical report we describe the IDLAB top-scoring submissions f...
04/06/2019

Large Margin Softmax Loss for Speaker Verification

In neural network based speaker verification, speaker embedding is expec...
05/02/2018

End-to-End Residual CNN with L-GM Loss Speaker Verification System

We propose an end-to-end speaker verification system based on the neural...
11/03/2021

STC speaker recognition systems for the NIST SRE 2021

This paper presents a description of STC Ltd. systems submitted to the N...
03/28/2022

Investigation of Different Calibration Methods for Deep Speaker Embedding based Verification Systems

Deep speaker embedding extractors have already become new state-of-the-a...
02/02/2021

A Speaker Verification Backend with Robust Performance across Conditions

In this paper, we address the problem of speaker verification in conditi...
11/26/2019

A discriminative condition-aware backend for speaker verification

We present a scoring approach for speaker verification that mimics the s...