Speech World Model: Causal State–Action Planning with Explicit Reasoning for Speech

Xuanru Zhou, Jiachen Lian, Henry Hong, Xinyi Yang, Gopala Anumanchipalli

Keywords: speech, spoken language understanding, state-action, causal reasoning

Abstract: Current speech-language models (SLMs) typically use a cascade of speech encoder and large language model, treating speech understanding as a single black box. They analyze the content of speech well but reason weakly about other aspects, especially under sparse supervision. Thus, we argue for explicit reasoning over speech states and actions with modular and transparent decisions. Inspired by cognitive science we adopt a modular perspective and a world model view in which the system learns forward dynamics over latent states. We factorize speech understanding into four modules that communicate through a causal graph, establishing a cognitive state search space. Guided by posterior traces from this space, an instruction-tuned language model produces a concise causal analysis and a user-facing response, enabling counterfactual interventions and interpretability under partial supervision. We present the first graph based modular speech model for explicit reasoning and we will open source the model and data to promote the development of advanced speech understanding.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 7485