# DENOASR: Debiasing ASRs through Selective Denoising

arXiv: https://arxiv.org/abs/2410.16712 · HTML: https://mlsanity.com/paper/2410.16712/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 63 references that are in the map.
- First posted on arXiv 22 Oct 2024.

## Builds on (most cited first, 18 of 18)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation](https://mlsanity.com/paper/2008.09586/) (2020)
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021)
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021)
- [Learning Fast Adaptation on Cross-Accented Speech Recognition](https://mlsanity.com/paper/2003.01901/) (2020)
- [Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities](https://mlsanity.com/paper/2207.11345/) (2022)
- [Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance](https://mlsanity.com/paper/1908.08717/) (2019)
- [Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning](https://mlsanity.com/paper/2210.15324/) (2022)
- [Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review](https://mlsanity.com/paper/2211.09511/) (2022)
- [A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos](https://mlsanity.com/paper/2307.10587/) (2023)
- [Speech Enhancement based on Denoising Autoencoder with Multi-branched Encoders](https://mlsanity.com/paper/2001.01538/) (2020)
- [TENET: A Time-reversal Enhancement Network for Noise-robust ASR](https://mlsanity.com/paper/2107.01531/) (2021)

## Built on by (most cited first, 3 of 3)

- [Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning](https://mlsanity.com/paper/2506.17525/) (2025)
- [ASR Under the Stethoscope: Evaluating Biases in Clinical Speech Recognition across Indian Languages](https://mlsanity.com/paper/2512.10967/) (2025)
- [When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems](https://mlsanity.com/paper/2512.17562/) (2025)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) systems have been examined and shown to exhibit biases toward particular groups of individuals, influenced by factors such as demographic traits, accents, and speech styles. Noise can disproportionately impact speakers with certain accents, dialects, or speaking styles, leading to biased error rates. In this work, we introduce a novel framework DENOASR, which is a selective denoising technique to reduce the disparity in the word error rates between the two gender groups, male and female. We find that a combination of two popular speech denoising techniques, viz. DEMUCS and LE, can be effectively used to mitigate ASR disparity without compromising their overall performance. Experiments using two state-of-the-art open-source ASRs - OpenAI WHISPER and NVIDIA NEMO - on multiple benchmark datasets, including TIE, VOX-POPULI, TEDLIUM, and FLEURS, show that there is a promising reduction in the average word error rate gap across the two gender groups. For a given dataset, the denoising is selectively applied on speech samples having speech intelligibility below a certain threshold, estimated using a small validation sample, thus ameliorating the need for large-scale human-written ground-truth transcripts. Our findings suggest that selective denoising can be an elegant approach to mitigate biases in present-day ASR systems.