Towards Personalized Federated Learning for Dysarthric Speech Recognition
This paper proposes two aggregation strategies for personalizing federated learning-based ASR for dysarthric speakers.
The paper introduces two novel aggregation strategies for personalizing federated learning-based ASR for dysarthric speakers.
Before reading this…
Applications
- →speech recognition for dysarthric speakers
To understand this paper, make sure you know these concepts first:
- federated learningfind papers →
- speech recognitionfind papers →
Abstract
More Like ThisSpeech recognition is challenging for dysarthric speakers. While federated learning (FL)-based ASR can be an effective tool for protecting privacy, it suffers from heterogeneity issues caused by speaker variability. Forcing all speakers to share the same model components can be suboptimal under such heterogeneity, making personalization a promising direction; however, related research on dysarthric speech remains limited. To this end, this paper explores two aggregation strategies to achieve personalization, including the parameter-based averaging strategy and the embedding-based averaging strategy. Experiments on UASpeech and TORGO show that the proposed methods outperform the baseline regularized FedAvg by statistically significant WER reductions of up to 0.99% absolute (3.15% relative) on UASpeech and 0.56% absolute (4.73% relative) on TORGO, respectively.