Seamless Dysfluent Speech Text Alignment for Disordered Speech Analysis

TL;DR

This paper introduces Neural LCS, a novel phoneme-level alignment method that improves the accuracy of aligning dysfluent speech with intended text, aiding diagnosis of speech disorders.

Contribution

Neural LCS is a new approach that effectively models phoneme similarities and handles partial and context-aware alignment for dysfluent speech.

Findings

Neural LCS outperforms existing models in alignment accuracy.

It demonstrates robustness on both simulated and real PPA data.

Significantly improves dysfluent speech segmentation.

Abstract

Accurate alignment of dysfluent speech with intended text is crucial for automating the diagnosis of neurodegenerative speech disorders. Traditional methods often fail to model phoneme similarities effectively, limiting their performance. In this work, we propose Neural LCS, a novel approach for dysfluent text-text and speech-text alignment. Neural LCS addresses key challenges, including partial alignment and context-aware similarity mapping, by leveraging robust phoneme-level modeling. We evaluate our method on a large-scale simulated dataset, generated using advanced data simulation techniques, and real PPA data. Neural LCS significantly outperforms state-of-the-art models in both alignment accuracy and dysfluent speech segmentation. Our results demonstrate the potential of Neural LCS to enhance automated systems for diagnosing and analyzing speech disorders, offering a more accurate and linguistically grounded solution for dysfluent speech alignment.