sbintuitions/DuplexCascade

Native End-to-End Full-Duplex Spoken Language Model

[EMNLP 2026 Main] Speaking While Listening: a survey and empirical audit of full-duplex spoken dialogue systems — L0–L3 architectural hierarchy, T×I×R interaction ontology, and a five-state decision machine, with a curated list of models, datasets, and benchmarks.

Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

X-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech interaction with a lightweight, pure-Python, production-ready architecture.

A curated list of full-duplex spoken dialogue models & benchmarks

Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems

J-Moshi: A Japanese Full-duplex Spoken Dialogue System

MichiAI: A Low Latency, Full Duplex Speech LLM with zero coherence loss