# Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models

arXiv: https://arxiv.org/abs/2606.11167 · HTML: https://mlsanity.com/paper/2606.11167/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 56 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 30 of 40)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM](https://mlsanity.com/paper/2411.00774/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech](https://mlsanity.com/paper/2409.09305/) (2024)
- [MinMo: A Multimodal Large Language Model for Seamless Voice Interaction](https://mlsanity.com/paper/2501.06282/) (2025)
- [Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents](https://mlsanity.com/paper/2409.15594/) (2024)
- [PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models](https://mlsanity.com/paper/2602.06053/) (2026)
- [Voice Activity Projection: Self-supervised Learning of Turn-taking Events](https://mlsanity.com/paper/2205.09812/) (2022)
- [SpeechAlign: Aligning Speech Generation to Human Preferences](https://mlsanity.com/paper/2404.05600/) (2024)
- [Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics](https://mlsanity.com/paper/2503.01174/) (2025)
- [Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner](https://mlsanity.com/paper/2510.07838/) (2025)
- [SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model](https://mlsanity.com/paper/2505.15670/) (2025)
- [SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation](https://mlsanity.com/paper/2505.17060/) (2025)
- [ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction](https://mlsanity.com/paper/2511.08723/) (2025)
- [Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2411.01834/) (2024)
- [MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models](https://mlsanity.com/paper/2511.10262/) (2025)
- [NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction](https://mlsanity.com/paper/2506.00975/) (2025)
- [FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems](https://mlsanity.com/paper/2502.13472/) (2025)

## Built on by (most cited first, 10 of 10)

- [Full-Duplex Speech Models Take the Floor When Asked, Not When Needed](https://mlsanity.com/paper/2609.19596/) (2026)
- [DuplexJail: Safety Alignment Breaks Under Spoken Interruption in Full-Duplex Models](https://mlsanity.com/paper/2609.09420/) (2026)
- [SteerDuplex: Steerable Duplex Speech Dialogue Models](https://mlsanity.com/paper/2609.12623/) (2026)
- [Causal Analysis and Mitigation of Spurious Onsets in Full-Duplex Speech LLMs](https://mlsanity.com/paper/2609.13445/) (2026)
- [Controlling Backchannels in Streamable Full-duplex Models](https://mlsanity.com/paper/2609.29418/) (2026)
- [Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance](https://mlsanity.com/paper/2609.30773/) (2026)
- [IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages](https://mlsanity.com/paper/2609.31967/) (2026)
- [Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue](https://mlsanity.com/paper/2610.08683/) (2026)
- [SteerablePlex: Can We Steer Full-Duplex Models?](https://mlsanity.com/paper/2610.12201/) (2026)
- [DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion](https://mlsanity.com/paper/2610.12214/) (2026)

## Abstract (arXiv)

Full-duplex spoken dialogue models can listen and speak simultaneously, making them a promising architecture for natural conversation. However, current models are trained solely with supervised learning through token-level likelihood maximization, which does not directly optimize interaction-level behaviors, causing interactivity issues such as excessive silence and ill-timed turn-taking. Recent work has applied reinforcement learning (RL) to improve interactivity, but existing methods address only a limited set of interactive behaviors in their rewards. In this work, we propose a post-training alignment method that comprehensively improves the interactivity of full-duplex spoken dialogue models through RL. We address the four canonical axes of interactivity: pause handling, turn-taking, backchanneling, and user interruption. For each axis, we extract short audio segments from human conversation corpora and optimize the model with axis-specific reward functions. An extra LLM-based reward for response quality prevents semantic degradation. We apply our method to two open-source models, Moshi and PersonaPlex, demonstrating consistent improvements in interactivity on both offline evaluation with pre-recorded audio and real-time multi-turn dialogue evaluation.