# "OK Aura, Be Fair With Me": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection

arXiv: https://arxiv.org/abs/2604.05830 · HTML: https://mlsanity.com/paper/2604.05830/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 52 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification](https://mlsanity.com/paper/2110.05777/) (2021)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [SpecMix : A Mixed Sample Data Augmentation method for Training withTime-Frequency Domain Features](https://mlsanity.com/paper/2108.03020/) (2021)
- [Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities](https://mlsanity.com/paper/2207.11345/) (2022)
- [Towards measuring fairness in speech recognition: Fair-Speech dataset](https://mlsanity.com/paper/2408.12734/) (2024)
- [Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps](https://mlsanity.com/paper/2402.17954/) (2024)
- [Leveraging Self-Supervised Learning for Speaker Diarization](https://mlsanity.com/paper/2409.09408/) (2024)
- [Gender Bias in Depression Detection Using Audio Features](https://mlsanity.com/paper/2010.15120/) (2020)
- [Don't speak too fast: The impact of data bias on self-supervised speech models](https://mlsanity.com/paper/2110.07957/) (2021)
- [On the social bias of speech self-supervised models](https://mlsanity.com/paper/2406.04997/) (2024)
- [Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech](https://mlsanity.com/paper/2405.06150/) (2024)
- [Device-Robust Acoustic Scene Classification via Impulse Response Augmentation](https://mlsanity.com/paper/2305.07499/) (2023)
- [Exploring data augmentation in bias mitigation against non-native-accented speech](https://mlsanity.com/paper/2312.15499/) (2023)
- [A Contrastive Learning Approach to Mitigate Bias in Speech Models](https://mlsanity.com/paper/2406.14686/) (2024)
- [FilterAugment: An Acoustic Environmental Data Augmentation Method](https://mlsanity.com/paper/2110.03282/) (2021)
- [Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows](https://mlsanity.com/paper/2201.07677/) (2022)
- [Fairness of Automatic Speech Recognition: Looking Through a Philosophical Lens](https://mlsanity.com/paper/2508.07143/) (2025)
- [Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation](https://mlsanity.com/paper/2210.15226/) (2022)
- [A Brief Tutorial on Sample Size Calculations for Fairness Audits](https://mlsanity.com/paper/2312.04745/) (2023)
- [Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles](https://mlsanity.com/paper/2310.11379/) (2023)
- [On the Use of Audio to Improve Dialogue Policies](https://mlsanity.com/paper/2410.13385/) (2024)

## Abstract (arXiv)

Voice-based interfaces are widely used; however, achieving fair Wake-up Word detection across diverse speaker populations remains a critical challenge due to persistent demographic biases. This study evaluates the effectiveness of demographics-agnostic training techniques in mitigating performance disparities among speakers of varying sex, age, and accent. We utilize the OK Aura database for our experiments, employing a training methodology that excludes demographic labels, which are reserved for evaluation purposes. We explore (i) data augmentation techniques to enhance model generalization and (ii) knowledge distillation of pre-trained foundational speech models. The experimental results indicate that these demographics-agnostic training techniques markedly reduce demographic bias, leading to a more equitable performance profile across different speaker groups. Specifically, one of the evaluated techniques achieves a Predictive Disparity reduction of 39.94% for sex, 83.65% for age, and 40.48% for accent when compared to the baseline. This study highlights the effectiveness of label-agnostic methodologies in fostering fairness in Wake-up Word detection.