mlsanityData to 19 Oct 2026

ASR evaluation, bias and atypical speech

644 papers3 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: speech, asr, recognition, speech recognition, automatic

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). 20 new papers 2 Oct–19 Oct.

What’s new

2 Oct – 19 Oct 2026

20 new papers, 2 Oct – 19 Oct; 3 this week.

  1. This week · 3
  2. How to get the best and fairest performance out of your ASR system using activation steering also fits: Speaker recognition and diarization
  3. AfriBED: a Speech Recognition Bias Evaluation Dataset for Low Resource African Languages also fits: Multilingual and low-resource ASR
  4. Conducting Reliable Keyword Estimation with Unreliable ASR in Police Audio Data also fits: Speech recognition models and training
  5. Earlier · 17
  6. Does Expert Supervision Improve Text-to-Speech? An Empirical Study of Preference Optimization also fits: Audio language models and spoken dialogue
  7. Dual Task Vector Merging: Leveraging Emotion and ASR Knowledge for Low-Resource Alzheimer's Disease Detection
  8. ASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects
  9. ASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act Classification also fits: Speech recognition models and training
  10. SITAR: A Situational Distortion Metric for Automatic Speech Recognition Evaluation also fits: Speech recognition models and training
  11. Automatic Sentence Completion Using Bengali Audio Speech with a Transformer-Based Early Speech Recognition System
  12. Connecting the Dots: Enduring Performance Gaps in ASR Systems Between Standard and Minority English Varieties also fits: Multilingual and low-resource ASR
All 20
  1. When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents
  2. Understanding Personalization Gains in Whisper also fits: Audio language models and spoken dialogue
  3. AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation also fits: Vocoders and speech synthesis
  4. Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR also fits: Multilingual and low-resource ASR
  5. Enhancing Speech Recognition through Text-to-Speech and Voice Conversion Augmentation
  6. Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear? also fits: Audio language models and spoken dialogue
  7. InterCorrect: Intersection-Aware Correction of Demographic Model Merging for Fair ASR also fits: Speech recognition models and training
  8. Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants also fits: Multilingual and low-resource ASR
  9. Augmenting Large Audio Language Models with Low-Level Acoustic Features for Dysarthric Speech Detection
  10. Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations

Foundations

Most cited by papers here

  1. Investigation of Data Augmentation Techniques for Disordered Speech Recognition2022cited by 38 here
  2. Quantifying Bias in Automatic Speech Recognition2021cited by 32 here
  3. Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition2022cited by 24 here
  4. Speaker adaptation for Wav2vec2 based dysarthric ASR2022cited by 24 here
  5. Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding2021cited by 23 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 32 here
  2. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 27 here
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 266 here
  4. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 18 here
  5. 2023Scaling Speech Technology to 1,000+ Languagescited by 34 here
19 more it builds on, not in this chain
  1. 2021End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Studycited by 22 here
  2. 2021Quantifying Bias in Automatic Speech Recognitioncited by 32 here
  3. 2021Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understandingcited by 23 here
  4. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 22 here
  5. 2021Adversarial Data Augmentation for Disordered Speech Recognitioncited by 20 here
  6. 2021Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasetscited by 19 here
  7. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 69 here
  8. 2021Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptionscited by 19 here
  9. 2022Investigation of Data Augmentation Techniques for Disordered Speech Recognitioncited by 38 here
  10. 2022Recent Progress in the CUHK Dysarthric Speech Recognition Systemcited by 23 here
  11. 2022Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognitioncited by 24 here
  12. 2022Speaker adaptation for Wav2vec2 based dysarthric ASRcited by 24 here
  13. 2022Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognitioncited by 19 here
  14. 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 20 here
  15. 2023Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognitioncited by 21 here
  16. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 22 here
  17. 2023Adaptation of Whisper models to child speech recognitioncited by 19 here
  18. 2024Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesiscited by 21 here
  19. 2024Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Modelscited by 21 here

The 24 most cited of 1,164.

Browse

30 of 644, ranked 6–35

  1. 6Recent Progress in the CUHK Dysarthric Speech Recognition System202223
  2. 7End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study202122
  3. 8Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis202421
  4. 9Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models202421
  5. 10Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition202321
  6. 11Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition202220
  7. 12Adversarial Data Augmentation for Disordered Speech Recognition202120
  8. 13Adaptation of Whisper models to child speech recognition202319
  9. 14Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition202219
  10. 15Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets202119
All 30
  1. 16Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions202119
  2. 17Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation202418
  3. 18Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults202318
  4. 19Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities202216
  5. 20Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition202215
  6. 21Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition202215
  7. 22SEP-28k: A Dataset for Stuttering Event Detection From Podcasts With People Who Stutter202115
  8. 23Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition202414
  9. 24Towards measuring fairness in speech recognition: Fair-Speech dataset202413
  10. 25A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition202213
  11. 26Earnings-21: A Practical Benchmark for ASR in the Wild202113
  12. 27Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps202412
  13. 28Use of Speech Impairment Severity for Dysarthric Speech Recognition202312
  14. 29Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric202112
  15. 30Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition202211
  16. 31Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition202211
  17. 32EasyCall corpus: a dysarthric speech dataset202111
  18. 33Model-Based Approach for Measuring the Fairness in ASR202111
  19. 34PhoWhisper: Automatic Speech Recognition for Vietnamese202410
  20. 35Accurate synthesis of Dysarthric Speech for ASR data augmentation202310