Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion

Ahmad, Aloradi,; Mack, Wolfgang; Elminshawi, Mohamed; Habets, Emanuël A. P.

doi:10.23919/eusipco55093.2022.9909705

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [7], target-speaker extraction [8] is applied in a joint training scheme with speaker verification to handle the significant speaker overlap. Another approach is used in [9], with an architecture injecting the target speaker embedding into the hidden frame-level features before the statistics pooling layer. However, these approaches use task-specific architectures or require significant adaptations of existing speaker verification pipelines.…”

Section: Introductionmentioning

confidence: 99%

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

Thienpondt

Desplanques

Demuynck

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

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 Vox-Celeb Speaker Recognition Challenge 2020.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Thienpondt

Desplanques

Demuynck

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

Margin-Mixup: A Method for Robust Speaker Verification In Multi-Speaker Audio

Thienpondt

Madhu

Demuynck

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper is concerned with the task of speaker verification on audio with multiple overlapping speakers. Most speaker verification systems are designed with the assumption of a single speaker being present in a given audio segment. However, in a real-world setting this assumption does not always hold. In this paper, we demonstrate that current speaker verification systems are not robust against audio with noticeable speaker overlap. To alleviate this issue, we propose marginmixup, a simple training strategy that can easily be adopted by existing speaker verification pipelines to make the resulting speaker embeddings robust against multi-speaker audio. In contrast to other methods, margin-mixup requires no alterations to regular speaker verification architectures, while attaining better results. On our multi-speaker test set based on VoxCeleb1, the proposed margin-mixup strategy improves the EER on average with 44.4% relative to our state-of-the-art speaker verification baseline systems.

show abstract

Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion

Cited by 2 publications

References 22 publications

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

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

Margin-Mixup: A Method for Robust Speaker Verification In Multi-Speaker Audio

Contact Info

Product

Resources

About