Enhancing Dysarthric Speech Recognition For Unseen Speakers Via Prototype-based Adaptation
2024 · Shiyao Wang, Shiwan Zhao, Jiaming Zhou, et al.
Abstract
Dysarthric speech recognition (DSR) presents a formidable challenge due to inherent inter-speaker variability, leading to severe performance degradation when applying DSR models to new dysarthric speakers. Traditional speaker adaptation methodologies typically involve fine-tuning models for each speaker, but this strategy is cost-prohibitive and inconvenient for disabled users, requiring substantial data collection. To address this issue, we introduce a prototype-based approach that markedly improves DSR performance for unseen dysarthric speakers without additional fine-tuning. Our method employs a feature extractor trained with HuBERT to produce per-word prototypes that encapsulate the characteristics of previously unseen speakers. These prototypes serve as the basis for classification. Additionally, we incorporate supervised contrastive learning to refine feature extraction. By enhancing representation quality, we further improve DSR performance, enabling effective personalized DSR.
Authors
(none)
Tags
Stats
Related papers
- On-the-fly Feature Based Rapid Speaker Adaptation For Dysarthric And Elderly Speech Recognition (2022)6.34
- Speaker Identity Preservation In Dysarthric Speech Reconstruction By Adversarial Speaker Adaptation (2022)0.00
- Speaker Adaptation Using Spectro-temporal Deep Features For Dysarthric And Elderly Speech Recognition (2022)12.02
- Homogeneous Speaker Features For On-the-fly Dysarthric And Elderly Speaker Adaptation (2024)0.00
- Structured Speaker-deficiency Adaptation Of Foundation Models For Dysarthric And Elderly Speech Recognition (2024)0.00
- UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization (2024)0.00
- Interpretable Dysarthric Speaker Adaptation Based On Optimal-transport (2022)2.26
- Parameter-efficient Dysarthric Speech Recognition Using Adapter Fusion And Householder Transformation (2023)0.00