# Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition

arXiv: https://arxiv.org/abs/2203.15431 · HTML: https://mlsanity.com/paper/2203.15431/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2022.

## Built on by (most cited first, 15 of 15)

- [Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2302.14564/) (2023)
- [Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2407.13782/) (2024)
- [Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task Learning](https://mlsanity.com/paper/2210.15387/) (2022)
- [Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context](https://mlsanity.com/paper/2403.20184/) (2024)
- [Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models](https://mlsanity.com/paper/2305.05201/) (2023)
- [Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test](https://mlsanity.com/paper/2305.13108/) (2023)
- [A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessment](https://mlsanity.com/paper/2306.04337/) (2023)
- [WavRx: a Disease-Agnostic, Generalizable, and Privacy-Preserving Speech Health Diagnostic Model](https://mlsanity.com/paper/2406.18731/) (2024)
- [Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation](https://mlsanity.com/paper/2407.06310/) (2024)
- [Idiosyncratic Versus Normative Modeling of Atypical Speech Recognition: Dysarthric Case Studies](https://mlsanity.com/paper/2509.16718/) (2025)
- [Speaker Embeddings as Individuality Proxy for Voice Stress Detection](https://mlsanity.com/paper/2306.05915/) (2023)
- [On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition](https://mlsanity.com/paper/2505.22072/) (2025)
- [Unified Acoustic Representations for Screening Neurological and Respiratory Pathologies from Voice](https://mlsanity.com/paper/2508.20717/) (2025)
- [Phonological Subspace Collapse Is Aetiology-Specific and Cross-Lingually Stable: Evidence from 3,374 Speakers](https://mlsanity.com/paper/2604.21706/) (2026)
- [SpeechDx: A Multi-Task Benchmark for Clinical Speech AI](https://mlsanity.com/paper/2606.17339/) (2026)

## Abstract (arXiv)

We investigate the performance of self-supervised pretraining frameworks on pathological speech datasets used for automatic speech recognition (ASR). Modern end-to-end models require thousands of hours of data to train well, but only a small number of pathological speech datasets are publicly available. A proven solution to this problem is by first pretraining the model on a huge number of healthy speech datasets and then fine-tuning it on the pathological speech datasets. One new pretraining framework called self-supervised learning (SSL) trains a network using only speech data, providing more flexibility in training data requirements and allowing more speech data to be used in pretraining. We investigate SSL frameworks such as the wav2vec 2.0 and WavLM models using different setups and compare their performance with different supervised pretraining setups, using two types of pathological speech, namely, Japanese electrolaryngeal and English dysarthric. Our results show that although SSL has shown success with minimally resourced healthy speech, we do not find this to be the case with pathological speech. The best supervised setup outperforms the best SSL setup by 13.9% character error rate in electrolaryngeal speech and 16.8% word error rate in dysarthric speech.