Year: 2025
Type: preprint
Abstract: Speech is humanity's strongest coordination technology, yet we rarely treat it as an engineered system.This thesis reframes speech as a toolchain-Intention → Compilation → Actuation → Feedback-and proposes Return on Expression (RoE), the realized state change per unit cost, as the organizing objective.We present (i) a formal state-space/control model of utterances as interventions on beliefs, goals, and commitments; (ii) an empirically calibrated affordance map that translates context variables (uncertainty, risk, expertise asymmetry, channel constraints) into design choices (framing, redundancy, prosody); (iii) a failure taxonomy with detectable signals and mitigation protocols; and (iv) a Speech IDE that instruments conversation with an LLM-in-the-loop intention compiler, ambiguity linters, a commitment type checker, and a grounding meter.We define standardized micro-protocols (e.g., Query → Calibrate → Commit; Goal → Constraint → Offer → Check) and preregistered experiments across lab and field settings to estimate treatment effects on RoE, commitment conversion, grounding depth, and rework.Bayesian hierarchical models support estimation and transportability across domains.Ethics features (consent-to-influence, bias audits, kill-switches) reduce misuse.If validated in preregistered A/B tests (≥20% CCR lift and ≥25% ambiguity-error reduction), this framework provides a measurable, reproducible way to teach speech as a craft-raising coordination reliability in education, healthcare, and operations while establishing RoE as a first-class design objective.
Author: Kyle Hyatt
Language: English
Subfield: Language and Linguistics
Field: Arts and Humanities
Domain: Social Sciences
Open Access status: gold
OpenAlex ID: W4413294359