# Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech

arXiv: https://arxiv.org/abs/2603.15988 · HTML: https://mlsanity.com/paper/2603.15988/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [The VoiceMOS Challenge 2022](https://mlsanity.com/paper/2203.11389/) (2022)
- [EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark](https://mlsanity.com/paper/2406.07162/) (2024)
- [EasyCall corpus: a dysarthric speech dataset](https://mlsanity.com/paper/2104.02542/) (2021)
- [NeuroVoz: a Castillian Spanish corpus of parkinsonian speech](https://mlsanity.com/paper/2403.02371/) (2024)
- [WARP-Q: Quality Prediction For Generative Neural Speech Codecs](https://mlsanity.com/paper/2102.10449/) (2021)
- [Accurate synthesis of Dysarthric Speech for ASR data augmentation](https://mlsanity.com/paper/2308.08438/) (2023)
- [Speech Intelligibility Classifiers from 550k Disordered Speech Samples](https://mlsanity.com/paper/2303.07533/) (2023)
- [Can we reconstruct a dysarthric voice with the large speech model Parler TTS?](https://mlsanity.com/paper/2506.04397/) (2025)
- [On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs](https://mlsanity.com/paper/2503.03304/) (2025)
- [Voice Quality Dimensions as Interpretable Primitives for Speaking Style for Atypical Speech and Affect](https://mlsanity.com/paper/2505.21809/) (2025)
- [Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching](https://mlsanity.com/paper/2506.16127/) (2025)
- [JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairs](https://mlsanity.com/paper/2507.11636/) (2025)
- [Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech](https://mlsanity.com/paper/2508.17980/) (2025)

## Built on by (most cited first, 2 of 2)

- [Training-Free Cross-Lingual Dysarthria Severity Assessment via Phonological Subspace Analysis in Self-Supervised Speech Representations](https://mlsanity.com/paper/2604.10123/) (2026)
- [Phonological Subspace Collapse Is Aetiology-Specific and Cross-Lingually Stable: Evidence from 3,374 Speakers](https://mlsanity.com/paper/2604.21706/) (2026)

## Abstract (arXiv)

Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evaluation is costly and difficult to scale, and the scarcity of labeled data limits robust objective modeling. To address this, we propose a three-stage framework that leverages unlabeled dysarthric speech and large-scale typical speech datasets to scale training. A teacher model first generates pseudo-labels for unlabeled samples, followed by weakly supervised pretraining using a label-aware contrastive learning strategy that exposes the model to diverse speakers and acoustic conditions. The pretrained model is then fine-tuned for the downstream DSQA task. Experiments on five unseen datasets spanning multiple etiologies and languages demonstrate the robustness of our approach. Our Whisper-based baseline significantly outperforms SOTA DSQA predictors such as SpICE, and the full framework achieves an average SRCC of 0.761 across unseen test datasets.