Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912857382191104 |
|---|---|
| author | Yu, Haoyuan Chen, Yuxuan Cai, Minjie |
| author_facet | Yu, Haoyuan Chen, Yuxuan Cai, Minjie |
| contents | Full-duplex voice interaction is crucial for natural human computer interaction. We present a framework that decomposes complex dialogue into minimal conversational units, enabling the system to process each unit independently and predict when to transit to the next. This framework is instantiated as a semi-cascaded full-duplex dialogue system built around a multimodal large language model, supported by auxiliary modules such as voice activity detection (VAD) and text-to-speech (TTS) synthesis. The resulting system operates in a train-free, plug-and-play manner. Experiments on the HumDial dataset demonstrate the effectiveness of our framework, which ranks second among all teams on the test set of the Human-like Spoken Dialogue Systems Challenge (Track 2: Full-Duplex Interaction). Code is available at the GitHub repository https://github.com/yu-haoyuan/fd-badcat. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20230 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems Yu, Haoyuan Chen, Yuxuan Cai, Minjie Computation and Language Human-Computer Interaction Full-duplex voice interaction is crucial for natural human computer interaction. We present a framework that decomposes complex dialogue into minimal conversational units, enabling the system to process each unit independently and predict when to transit to the next. This framework is instantiated as a semi-cascaded full-duplex dialogue system built around a multimodal large language model, supported by auxiliary modules such as voice activity detection (VAD) and text-to-speech (TTS) synthesis. The resulting system operates in a train-free, plug-and-play manner. Experiments on the HumDial dataset demonstrate the effectiveness of our framework, which ranks second among all teams on the test set of the Human-like Spoken Dialogue Systems Challenge (Track 2: Full-Duplex Interaction). Code is available at the GitHub repository https://github.com/yu-haoyuan/fd-badcat. |
| title | Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.20230 |