DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition

TL;DR

This paper introduces DyPCL, a novel phoneme-level contrastive learning method with dynamic curriculum training, significantly improving dysarthric speech recognition by capturing invariant features across diverse speakers.

Contribution

It proposes a new phoneme-level contrastive learning framework with dynamic curriculum learning, addressing speaker variability in dysarthric speech recognition.

Findings

Achieves 22.10% relative reduction in WER on UASpeech dataset.

Outperforms baseline models in dysarthric speech recognition.

Demonstrates effectiveness of phoneme-level contrastive learning with dynamic difficulty adjustment.

Abstract

Dysarthric speech recognition often suffers from performance degradation due to the intrinsic diversity of dysarthric severity and extrinsic disparity from normal speech. To bridge these gaps, we propose a Dynamic Phoneme-level Contrastive Learning (DyPCL) method, which leads to obtaining invariant representations across diverse speakers. We decompose the speech utterance into phoneme segments for phoneme-level contrastive learning, leveraging dynamic connectionist temporal classification alignment. Unlike prior studies focusing on utterance-level embeddings, our granular learning allows discrimination of subtle parts of speech. In addition, we introduce dynamic curriculum learning, which progressively transitions from easy negative samples to difficult-to-distinguishable negative samples based on phonetic similarity of phoneme. Our approach to training by difficulty levels alleviates the inherent variability of speakers, better identifying challenging speeches. Evaluated on the UASpeech dataset, DyPCL outperforms baseline models, achieving an average 22.10\% relative reduction in word error rate (WER) across the overall dysarthria group.