{"ID":6621315,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12235","arxiv_id":"2607.12235","title":"A Semi-Automated System for Generating Dialogue-Based TTS Lessons Using Large Language Models: An Exploratory Study of Educational Potential","abstract":"This study proposes a semi-automated system for generating dialogue-based lessons using Large Language Models (LLMs) and Text-to-Speech (TTS) technology, and exploratorily examines its educational potential via a practical quasi-experiment. The system augments rather than replaces educators through a three-stage human-in-the-loop workflow (LLM-based slide/narration generation, educator review, automated audiovisual integration), and introduces a novel method for generating Expert-Novice dialogue narration based on cognitive apprenticeship theory. In a study of 245 first-year high school students who sequentially experienced three lesson formats (instructor voice, single-speaker TTS, dialogue TTS; content differed across sessions, limiting format/content separation), we conducted within-subject (Friedman test, N\u003c=183) and repeated cross-sectional (Mann-Whitney U, N=229/206) analyses. TTS audio did not substantially degrade the learning experience versus instructor voice, supported by TOST equivalence testing. Dialogue TTS was significantly superior to single TTS in comprehension (p=.006, q=.025) and cognitive engagement (p=.019, q=.048); enjoyment was non-significant after FDR correction (q=.081) but reached significance after controlling for prior knowledge (proportional-odds model, OR=1.65, q=.025), and these advantages were not attributable to prior-knowledge imbalance. Conversely, single TTS was superior in audio naturalness (p\u003c.001, q\u003c.001, r=-.238), revealing a trade-off between dialogue's benefits and higher extraneous cognitive load. Dialogue format was preferred by 66.9% of learners as most enjoyable (p\u003c.001). These results reflect a fixed-order design; replication is needed before generalizing them as effects of lesson format. This study provides a theoretical and empirical basis for the educational acceptability of TTS audio and for TTS lesson-format design.","short_abstract":"This study proposes a semi-automated system for generating dialogue-based lessons using Large Language Models (LLMs) and Text-to-Speech (TTS) technology, and exploratorily examines its educational potential via a practical quasi-experiment. The system augments rather than replaces educators through a three-stage human-...","url_abs":"https://arxiv.org/abs/2607.12235","url_pdf":"https://arxiv.org/pdf/2607.12235v1","authors":"[\"Gendo Kumoi\",\"Fumie Watanabe\",\"Tota Suko\",\"Takashi Ishida\",\"Yuko Kuma\",\"Manabu Kobayashi\",\"Shigeichi Hirasawa\"]","published":"2026-07-14T00:35:41Z","proceeding":"cs.CY","tasks":"[\"cs.CY\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}