Lyapunov Spectral Analysis of Speech Embedding Trajectories in Psychosis

2026/02/18 by Jelena Vasic, Branislav Andjelic, Ana Mancic +5 · 1 voice
Computer Science · Physics and Astronomy · #cs.CL #nlin.AO

paper · pdf · doi:10.48550/arxiv.2602.16273

Abstract

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.

Citations

• Multilingual E5 Text Embeddings: A Technical Report
• BERTić -- The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs
• Pattern formation outside of equilibrium
• Universality and scaling in gravitational collapse of a massless scalar field
• Determining Lyapunov exponents from a time series
• Lyapunov Characteristic Exponents for smooth dynamical systems and for hamiltonian systems; a method for computing all of them. Part 1: Theory
• Lyapunov Characteristic Exponents for smooth dynamical systems and for hamiltonian systems; A method for computing all of them. Part 2: Numerical application
• Topology of cosmic domains and strings
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Divergence measures based on the Shannon entropy

Discussions

• Vasic, Andjelic, Mancic, Djurdjevic, Mihic, Kovacevic, Maric, Maluckov: Lyapunov Spectral Analysis of Speech Embedding Trajectories in Psychosis https://arxiv.org/abs/2602.16273 https://arxiv.org/pdf/ [bsky, 0 points, 0 comments]

Related

• Representations Matter: Embedding Modes of Large Language Models using Dynamic Mode Decomposition
• Changes in the structure of spontaneous speech predict the disruption of hierarchical brain organization in first‐episode psychosis
• Inverted Vocal Tract Variables and Facial Action Units to Quantify Neuromotor Coordination in Schizophrenia
• Assessing dimensions of thought disorder with large language models: The tradeoff of accuracy and consistency
• A Graph Signal Processing Framework for Hallucination Detection in Large Language Models