A Study on Bias and Fairness In Deep Speaker Recognition
Not on the map. Why?
Abstract (arXiv)
With the ubiquity of smart devices that use speaker recognition (SR) systems as a means of authenticating individuals and personalizing their services, fairness of SR systems has becomes an important point of focus. In this paper we study the notion of fairness in recent SR systems based on 3 popular and relevant definitions, namely Statistical Parity, Equalized Odds, and Equal Opportunity. We examine 5 popular neural architectures and 5 commonly used loss functions in training SR systems, while evaluating their fairness against gender and nationality groups. Our detailed experiments shed light on this concept and demonstrate that more sophisticated encoder architectures better align with the definitions of fairness. Additionally, we find that the choice of loss functions can significantly impact the bias of SR models.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 14 Mar 2023.
Builds on
20 of 24 references.
References · 20
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
- 2020In defence of metric learning for speaker recognitioncited by 123
- 2014Return of the Devil in the Details: Delving Deep into Convolutional Netscited by 122
- 2020Speaker Recognition Based on Deep Learning: An Overviewcited by 59
- 2022Pushing the limits of raw waveform speaker recognitioncited by 49
- 2018Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition Systemcited by 45
- 2021Personalization Strategies for End-to-End Speech Recognition Systemscited by 26
- 2020The ins and outs of speaker recognition: lessons from VoxSRC 2020cited by 21
8 more
- 2022Bias in Automated Speaker Recognitioncited by 20
- 2019Delving into VoxCeleb: environment invariant speaker recognitioncited by 13
- 2022Improving fairness in speaker verification via Group-adapted Fusion Networkcited by 11
- 2020Siamese Capsule Network for End-to-End Speaker Recognition In The Wildcited by 6
- 2019A Deep Neural Network for Short-Segment Speaker Recognitioncited by 5
- 2021Improving Fairness in Speaker Recognitioncited by 5
- 2021SVEva Fair: A Framework for Evaluating Fairness in Speaker Verificationcited by 2
- 2022Fine-grained Early Frequency Attention for Deep Speaker Recognitioncited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.