analiza aiqbench
The paper presents a multilingual pipeline that uses an LLM for script generation and text-to-speech for narration to produce bedtime sleep stories. Its main contribution is engineering: deterministic planning, guardrails, quarantine of failed outputs, and a loudness-gated publication step, with explicit disclaimers that no clinical efficacy is claimed. For AI readers, it is a useful example of how to build constrained generative audio around weak evidence, though the sleep benefit itself remains unproven.
Nedimo: An Evidence-Grounded Multilingual Pipeline for AI-Generated Sleep Stories
arXiv:2610.40970v1 Announce Type: new Abstract: Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives (retention, completion, and novelty) are poorly aligned with the goal of supporting a transition toward sleep. Direct evidence for narrated bedtime audio in adults is mixed, and a recent active-controlled trial did not support such audio as a standalone treatment for sleep disturbance. We translate this uncertain evidence into conservative engineering requirements and present a multilingual pipeline for generating and narrating low-arousal sleep stories. The implemented prototype separates deterministic planning from large language model generation, represents content and delivery parameters explicitly, shapes each script through a four-phase attention taper, validates structural and lexical constraints, performs a bounded error-aware retry, and quarantines unresolved outputs. Provider-agnostic text-to-speech synthesis is followed by paragraph-aware joining, two-pass loudness normalization, and a publication gate that re-measures the saved, encoded file against fixed loudness, loudness-range, and true-peak limits. The product data model records stop position, replay, early abandonment, and completion while treating these events as ambiguous behavioral proxies rather than clinical outcomes. We contribute an evidence-to-requirement mapping, a traceable guardrail architecture with explicit acceptance thresholds, technical evaluation criteria, and a prospective protocol for testing sleep-onset effects. No clinical efficacy is claimed; the system is positioned as a relaxation and attentional-support tool whose benefit and possible reliance must be evaluated empirically.
Abstract:Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives (retention, completion, and novelty) are poorly aligned with the goal of supporting a transition toward sleep. Direct evidence for narrated bedtime audio in adults is mixed, and a recent active-controlled trial did not support such audio as a standalone treatment for sleep disturbance. We translate this uncertain evidence into conservative engineering requirements and present a multilingual pipeline for generating and narrating low-arousal sleep stories. The implemented prototype separates deterministic planning from large language model generation, represents content and delivery parameters explicitly, shapes each script through a four-phase attention taper, validates structural and lexical constraints, performs a bounded error-aware retry, and quarantines unresolved outputs. Provider-agnostic text-to-speech synthesis is followed by paragraph-aware joining, two-pass loudness normalization, and a publication gate that re-measures the saved, encoded file against fixed loudness, loudness-range, and true-peak limits. The product data model records stop position, replay, early abandonment, and completion while treating these events as ambiguous behavioral proxies rather than clinical outcomes. We contribute an evidence-to-requirement mapping, a traceable guardrail architecture with explicit acceptance thresholds, technical evaluation criteria, and a prospective protocol for testing sleep-onset effects. No clinical efficacy is claimed; the system is positioned as a relaxation and attentional-support tool whose benefit and possible reliance must be evaluated empirically.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Sound (cs.SD)
arXiv:2610.40970 [cs.AI]
(or arXiv:2610.40970v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.40970 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 321 cuvinte