# ASR evaluation, bias and atypical speech

Area: [Speech and audio language models](https://mlsanity.com/speech/index.md). HTML: https://mlsanity.com/speech/asr-evaluation-bias-and-atypical-speech/

## Key facts

- ASR evaluation, bias and atypical speech: 644 papers on arXiv since 2021 (data through 19 Oct 2026).
- 38 of its 644 mapped papers (6%) cite “Investigation of Data Augmentation Techniques for Disordered Speech Recognition” (2022, arXiv 2201.05562).
- 32 of its 644 mapped papers (5%) cite “Quantifying Bias in Automatic Speech Recognition” (2021, arXiv 2103.15122).
- 20 new papers 2 Oct–19 Oct.

## Most cited here

- [Investigation of Data Augmentation Techniques for Disordered Speech Recognition](https://mlsanity.com/paper/2201.05562/) (2022), cited by 38 papers here
- [Quantifying Bias in Automatic Speech Recognition](https://mlsanity.com/paper/2103.15122/) (2021), cited by 32 papers here
- [Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2202.10290/) (2022), cited by 24 papers here
- [Speaker adaptation for Wav2vec2 based dysarthric ASR](https://mlsanity.com/paper/2204.00770/) (2022), cited by 24 papers here
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021), cited by 23 papers here
- [Recent Progress in the CUHK Dysarthric Speech Recognition System](https://mlsanity.com/paper/2201.05845/) (2022), cited by 23 papers here
- [End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study](https://mlsanity.com/paper/2102.09918/) (2021), cited by 22 papers here
- [Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2302.14564/) (2023), cited by 21 papers here
- [Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis](https://mlsanity.com/paper/2406.08568/) (2024), cited by 21 papers here
- [Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models](https://mlsanity.com/paper/2406.10507/) (2024), cited by 21 papers here

## New (2 Oct–19 Oct)

- [How to get the best and fairest performance out of your ASR system using activation steering](https://mlsanity.com/paper/2610.26994/) (2026-10-19)
- [AfriBED: a Speech Recognition Bias Evaluation Dataset for Low Resource African Languages](https://mlsanity.com/paper/2610.26821/) (2026-10-19)
- [Conducting Reliable Keyword Estimation with Unreliable ASR in Police Audio Data](https://mlsanity.com/paper/2610.26614/) (2026-10-19)
- [Does Expert Supervision Improve Text-to-Speech? An Empirical Study of Preference Optimization](https://mlsanity.com/paper/2610.25292/) (2026-10-18)
- [Dual Task Vector Merging: Leveraging Emotion and ASR Knowledge for Low-Resource Alzheimer's Disease Detection](https://mlsanity.com/paper/2610.24870/) (2026-10-17)
- [ASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects](https://mlsanity.com/paper/2610.24572/) (2026-10-17)
- [ASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act Classification](https://mlsanity.com/paper/2610.22934/) (2026-10-16)
- [SITAR: A Situational Distortion Metric for Automatic Speech Recognition Evaluation](https://mlsanity.com/paper/2610.21440/) (2026-10-15)
- [Automatic Sentence Completion Using Bengali Audio Speech with a Transformer-Based Early Speech Recognition System](https://mlsanity.com/paper/2610.21164/) (2026-10-15)
- [Connecting the Dots: Enduring Performance Gaps in ASR Systems Between Standard and Minority English Varieties](https://mlsanity.com/paper/2610.17761/) (2026-10-13)
- [When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents](https://mlsanity.com/paper/2610.17619/) (2026-10-13)
- [Understanding Personalization Gains in Whisper](https://mlsanity.com/paper/2610.17019/) (2026-10-12)
- [AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation](https://mlsanity.com/paper/2610.14479/) (2026-10-10)
- [Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR](https://mlsanity.com/paper/2610.13807/) (2026-10-09)
- [Enhancing Speech Recognition through Text-to-Speech and Voice Conversion Augmentation](https://mlsanity.com/paper/2610.13662/) (2026-10-09)
- [Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?](https://mlsanity.com/paper/2610.13550/) (2026-10-09)
- [InterCorrect: Intersection-Aware Correction of Demographic Model Merging for Fair ASR](https://mlsanity.com/paper/2610.08604/) (2026-10-06)
- [Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants](https://mlsanity.com/paper/2610.06587/) (2026-10-05)
- [Augmenting Large Audio Language Models with Low-Level Acoustic Features for Dysarthric Speech Detection](https://mlsanity.com/paper/2610.03352/) (2026-10-02)
- [Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations](https://mlsanity.com/paper/2610.03017/) (2026-10-02)