Lyapunov Spectral Analysis of Speech Embedding Trajectories in Psychosis
This work provides a physics-inspired probe for disordered cognition in psychosis, though it is incremental as it applies existing dynamical systems methods to speech data.
The study tackled the problem of distinguishing psychotic from healthy speech by analyzing speech embeddings as a high-dimensional dynamical process, using Lyapunov exponent spectra, and found that these invariants robustly separate the two groups with stability across different embedding models.
We analyze speech embeddings from structured clinical interviews of psychotic patients and healthy controls by treating language production as a high-dimensional dynamical process. Lyapunov exponent (LE) spectra are computed from word-level and answer-level embeddings generated by two distinct large language models, allowing us to assess the stability of the conclusions with respect to different embedding presentations. Word-level embeddings exhibit uniformly contracting dynamics with no positive LE, while answer-level embeddings, in spite of the overall contraction, display a number of positive LEs and higher-dimensional attractors. The resulting LE spectra robustly separate psychotic from healthy speech, while differentiation within the psychotic group is not statistically significant overall, despite a tendency of the most severe cases to occupy distinct dynamical regimes. These findings indicate that nonlinear dynamical invariants of speech embeddings provide a physics-inspired probe of disordered cognition whose conclusions remain stable across embedding models.