A survey proposing an L0-L3 architectural hierarchy, T×I×R interaction ontology, and IDLE/LISTEN/SPEAK/WAIT/DUAL decision state machine for full-duplex spoken dialogue systems, documenting a realization gap between architectural potential and observed behavior due to training data limits.
acoustic to- kens
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
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.
years
2026 7representative citing papers
LWS is a text-first paradigm for full-duplex speech LLMs that treats visible writing as a primary output channel alongside audio input and spoken response, implemented via token schema and synthetic per-second annotations.
F-Actor is the first open instruction-following full-duplex conversational speech model, trained by freezing the audio encoder and finetuning only the language model on 2000 hours of data, with public release of model and code.
Lychee-FD resolves modality interference in full-duplex spoken language models by separating acoustic and semantic parameters in deep layers and adding a dense semantic alignment channel, achieving state-of-the-art performance on spoken QA and interaction benchmarks.
Next-Turn introduces time-to-next-speech-onset prediction for duration-aware streaming endpoint detection, reporting a 25.9% improvement in accuracy within 320 ms.
A multi-axis RL alignment technique improves pause handling, turn-taking, backchanneling, and interruption response in full-duplex spoken dialogue models by optimizing axis-specific rewards derived from human audio segments.
IRAF introduces an adaptive fusion module that uses a predicted scalar reliability gate to reduce the impact of interfering speakers on user audio representations in end-to-end full-duplex spoken dialogue systems, with reported gains on MS-MARCO and InstructS2S-200K.
citing papers explorer
-
A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine
A survey proposing an L0-L3 architectural hierarchy, T×I×R interaction ontology, and IDLE/LISTEN/SPEAK/WAIT/DUAL decision state machine for full-duplex spoken dialogue systems, documenting a realization gap between architectural potential and observed behavior due to training data limits.
-
Liberating LLM Capabilities in Full-Duplex Speech Models
LWS is a text-first paradigm for full-duplex speech LLMs that treats visible writing as a primary output channel alongside audio input and spoken response, implemented via token schema and synthetic per-second annotations.
-
F-Actor: Controllable Conversational Behaviour in Full-Duplex Models
F-Actor is the first open instruction-following full-duplex conversational speech model, trained by freezing the audio encoder and finetuning only the language model on 2000 hours of data, with public release of model and code.
-
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
Lychee-FD resolves modality interference in full-duplex spoken language models by separating acoustic and semantic parameters in deep layers and adding a dense semantic alignment channel, achieving state-of-the-art performance on spoken QA and interaction benchmarks.
-
Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction
Next-Turn introduces time-to-next-speech-onset prediction for duration-aware streaming endpoint detection, reporting a 25.9% improvement in accuracy within 320 ms.
-
Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
A multi-axis RL alignment technique improves pause handling, turn-taking, backchanneling, and interruption response in full-duplex spoken dialogue models by optimizing axis-specific rewards derived from human audio segments.
-
IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems
IRAF introduces an adaptive fusion module that uses a predicted scalar reliability gate to reduce the impact of interfering speakers on user audio representations in end-to-end full-duplex spoken dialogue systems, with reported gains on MS-MARCO and InstructS2S-200K.