DLIOS: An LLM-Augmented Real-Time Multi-Modal Interactive Enhancement Overlay System for Douyin Live Streaming
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914365654958080 |
|---|---|
| author | Wen, Shuide Seok, Sungil Ku, Beier Li, Richee He, Yubin Qu, Bowen Yang, Yang Su, Ping Jiao, Can |
| author_facet | Wen, Shuide Seok, Sungil Ku, Beier Li, Richee He, Yubin Qu, Bowen Yang, Yang Su, Ping Jiao, Can |
| contents | We present DLIOS, a Large Language Model (LLM)-augmented real-time multi-modal interactive enhancement overlay system for Douyin (TikTok) live streaming. DLIOS employs a three-layer transparent window architecture for independent rendering of danmaku (scrolling text), gift and like particle effects, and VIP entrance animations, built around an event-driven WebView2 capture pipeline and a thread-safe event bus. On top of this foundation we contribute an LLM broadcast automation framework comprising: (1) a per-song four-segment prompt scheduling system (T1 opening/transition, T2 empathy, T3 era story/production notes, T4 closing) that generates emotionally coherent radio-style commentary from lyric metadata; (2) a JSON-serializable RadioPersonaConfig schema supporting hot-swap multi-persona broadcasting; (3) a real-time danmaku quick-reaction engine with keyword routing to static urgent speech or LLM-generated empathetic responses; and (4) the Suwan Li AI singer-songwriter persona case study -- over 100 AI-generated songs produced with Suno. A 36-hour stress test demonstrates: zero danmaku overlap, zero deadlock crashes, gift effect P95 latency <= 180 ms, LLM-to-TTS segment P95 latency <= 2.1 s, and TTS integrated loudness gain of 9.5 LUFS. live streaming; danmaku; large language model; prompt engineering; virtual persona; WebView2; WINMM; TTS; Suno; loudness normalization; real-time scheduling |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03060 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DLIOS: An LLM-Augmented Real-Time Multi-Modal Interactive Enhancement Overlay System for Douyin Live Streaming Wen, Shuide Seok, Sungil Ku, Beier Li, Richee He, Yubin Qu, Bowen Yang, Yang Su, Ping Jiao, Can Image and Video Processing Audio and Speech Processing We present DLIOS, a Large Language Model (LLM)-augmented real-time multi-modal interactive enhancement overlay system for Douyin (TikTok) live streaming. DLIOS employs a three-layer transparent window architecture for independent rendering of danmaku (scrolling text), gift and like particle effects, and VIP entrance animations, built around an event-driven WebView2 capture pipeline and a thread-safe event bus. On top of this foundation we contribute an LLM broadcast automation framework comprising: (1) a per-song four-segment prompt scheduling system (T1 opening/transition, T2 empathy, T3 era story/production notes, T4 closing) that generates emotionally coherent radio-style commentary from lyric metadata; (2) a JSON-serializable RadioPersonaConfig schema supporting hot-swap multi-persona broadcasting; (3) a real-time danmaku quick-reaction engine with keyword routing to static urgent speech or LLM-generated empathetic responses; and (4) the Suwan Li AI singer-songwriter persona case study -- over 100 AI-generated songs produced with Suno. A 36-hour stress test demonstrates: zero danmaku overlap, zero deadlock crashes, gift effect P95 latency <= 180 ms, LLM-to-TTS segment P95 latency <= 2.1 s, and TTS integrated loudness gain of 9.5 LUFS. live streaming; danmaku; large language model; prompt engineering; virtual persona; WebView2; WINMM; TTS; Suno; loudness normalization; real-time scheduling |
| title | DLIOS: An LLM-Augmented Real-Time Multi-Modal Interactive Enhancement Overlay System for Douyin Live Streaming |
| topic | Image and Video Processing Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.03060 |