FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems
This work solves the problem of enhancing naturalness and efficiency in human-machine speech interactions for dialogue system developers, though it is incremental as it builds on existing full-duplex approaches.
The paper tackles the problem of improving full-duplex speech dialogue systems by addressing issues like module coupling and noise interference, resulting in a 24.9% reduction in false interruption rate and a 7.6% improvement in response accuracy compared to baselines.
Full-Duplex Speech Dialogue Systems (Full-Duplex SDS) have significantly enhanced the naturalness of human-machine interaction by enabling real-time bidirectional communication. However, existing approaches face challenges such as difficulties in independent module optimization and contextual noise interference due to highly coupled architectural designs and oversimplified binary state modeling. This paper proposes FlexDuo, a flexible full-duplex control module that decouples duplex control from spoken dialogue systems through a plug-and-play architectural design. Furthermore, inspired by human information-filtering mechanisms in conversations, we introduce an explicit Idle state. On one hand, the Idle state filters redundant noise and irrelevant audio to enhance dialogue quality. On the other hand, it establishes a semantic integrity-based buffering mechanism, reducing the risk of mutual interruptions while ensuring accurate response transitions. Experimental results on the Fisher corpus demonstrate that FlexDuo reduces the false interruption rate by 24.9% and improves response accuracy by 7.6% compared to integrated full-duplex dialogue system baselines. It also outperforms voice activity detection (VAD) controlled baseline systems in both Chinese and English dialogue quality. The proposed modular architecture and state-based dialogue model provide a novel technical pathway for building flexible and efficient duplex dialogue systems.