ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models

• URL: http://arxiv.org/abs/2604.10065v1
• Date: Sat, 11 Apr 2026 07:07:08 GMT
• Title: ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
• Abstract summary: Empirical evaluations show ASPIRin optimize interactivity across turntaking, backchanneling, and pause handling.<n>We propose ASPIRin degrade turn to say when when to collapse when to say.
• Score: 49.18708573170585
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end full-duplex Speech Language Models (SLMs) require precise turn-taking for natural interaction. However, optimizing temporal dynamics via standard raw-token reinforcement learning (RL) degrades semantic quality, causing severe generative collapse and repetition. We propose ASPIRin, an interactivity-optimized RL framework that explicitly decouples when to speak from what to say. Using Action Space Projection, ASPIRin maps the text vocabulary into a coarse-grained binary state (active speech vs. inactive silence). By applying Group Relative Policy Optimization (GRPO) with rule-based rewards, it balances user interruption and response latency. Empirical evaluations show ASPIRin optimizes interactivity across turn-taking, backchanneling, and pause handling. Crucially, isolating timing from token selection preserves semantic coherence and reduces the portion of duplicate n-grams by over 50% compared to standard GRPO, effectively eliminating degenerative repetition.

Related papers

• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models [53.470209949659115]
  We propose a post-training alignment method that improves full spoken dialogue models through RL.<n>We address the four canonical axes of interactivity: handling turn-taking, back-channel pause, and user interruption.<n>An extra-based reward for response quality prevents semantic degradation.
  arXiv  Detail & Related papers  (2026-06-09T17:46:55Z)
• MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models [62.05118198431989]
  Asynchronous full-speech models are distinguished by their full-time interactivity and naturalness of AI pauses.<n>Our framework enables the model to identify knowledge-demand conversational queries and ground responses in external information.<n>Our design supports plug-and-play retrieval methods without retraining and demonstrates strong performance on out-of-toe reasoning tasks.
  arXiv  Detail & Related papers  (2026-04-14T16:17:52Z)
• GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization [5.5806589487812746]
  GDPO-Listener is a novel framework that achieves highly expressive speaking and listening motion generation.<n>We introduce an Auto-Regressive Flow Matching architecture enabling stable supervised learning.<n>By isolating reward normalization across distinct FLAME parameter groups, GDPO explicitly incentivizes high variance expressive generations.
  arXiv  Detail & Related papers  (2026-03-26T04:36:27Z)
• TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding [15.908533215017059]
  We present TagSpeech, a unified framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization.<n>The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that acts as a synchronization signal between semantic understanding and speaker tracking.
  arXiv  Detail & Related papers  (2026-01-11T12:40:07Z)
• FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction [49.83226596963294]
  Speech-computer human interaction enables real-time spoken dialogue systems.<n>Modelling and benchmarking these models remains a fundamental challenge.<n>We introduce FLEXI, the first benchmark for full-human spoken interaction.
  arXiv  Detail & Related papers  (2025-09-26T11:57:42Z)
• Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules [19.673388630963807]
  We formalise the challenge as span-conditioned generation, decomposing each turn into the dialogue history.<n>We introduce a quotation-centric data pipeline that automatically synthesises task-specific dialogues.<n>We propose QuAda, a lightweight training-based method that attaches two bottleneck projections to every attention head.
  arXiv  Detail & Related papers  (2025-05-30T07:06:11Z)
• Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis [64.12708207721276]
  We introduce a novel pseudo-autoregressive (PAR) language modeling approach that unifies AR and NAR modeling.<n>Building on PAR, we propose PALLE, a two-stage TTS system that leverages PAR for initial generation followed by NAR refinement.<n>Experiments demonstrate that PALLE, trained on LibriTTS, outperforms state-of-the-art systems trained on large-scale data.
  arXiv  Detail & Related papers  (2025-04-14T16:03:21Z)
• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities [93.09944267871163]
  FullDuplexBench is a benchmark that systematically evaluates key interactive behaviors.<n>By releasing our benchmark code we aim to advance spoken dialogue modeling and the development of more natural and engaging SDMs.
  arXiv  Detail & Related papers  (2025-03-06T18:59:16Z)
• Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF [14.2594830589926]
  Counterspeech, defined as a response to online hate speech, is increasingly used as a non-censorial solution. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. CoARL's first two phases involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech.
  arXiv  Detail & Related papers  (2024-03-15T08:03:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.