WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training

• URL: http://arxiv.org/abs/2604.14932v1
• Date: Thu, 16 Apr 2026 12:20:27 GMT
• Title: WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training
• Abstract summary: We propose a modality-aware adaptive post-training recipe for spoken dialogue.<n>It constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring.<n>We evaluate the method across multiple spoken dialogue benchmarks and representative architectures.
• Score: 42.85483422955689
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current open-source spoken dialogue models often remain below expectations. Motivated by the success of online reinforcement learning(RL) in other domains, one might attempt to directly apply preference optimization to spoken dialogue models, yet this transfer is non-trivial. We analyze these obstacles from the perspectives of reward modeling and rollout sampling, focusing on how sparse preference supervision interacts with dense speech generation under shared-parameter updates. Based on the analysis, we propose a modality-aware adaptive post-training recipe that makes RL practical for spoken dialogue: it constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring, while dynamically regulating their mixture from rollout statistics to avoid unreliable preference gradients. We evaluate the method across multiple spoken dialogue benchmarks and representative architectures, and observe consistent improvements in semantic quality and speech expressiveness.

Related papers

• 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)
• Covo-Audio Technical Report [61.09708870154148]
  Covo-Audio, a 7B-end LALM, directly processes continuous audio inputs and generates audio outputs within a single unified architecture.<n>Covo-Audio-Chat, a dialogue-oriented variant, demonstrates semantic strong spoken conversational abilities.
  arXiv  Detail & Related papers  (2026-02-10T14:31:11Z)
• Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback [82.70507055599093]
  We present the first systematic study of preference learning for improving SDS quality in both multi-turn Chain-of-Thought and blockwise duplex models.<n>Experiments show that single-reward RLAIF selectively improves its targeted metric, while joint multi-reward training yields consistent gains across semantic quality and audio naturalness.
  arXiv  Detail & Related papers  (2026-01-27T00:55:14Z)
• Aligning Spoken Dialogue Models from User Interactions [55.192134724622235]
  We propose a novel preference alignment framework to improve spoken dialogue models on realtime conversations from user interactions.<n>We create a dataset of more than 150,000 preference pairs from raw multi-turn speech conversations annotated with AI feedback.<n>Our findings shed light on the importance of a well-calibrated balance among various dynamics, crucial for natural real-time speech dialogue systems.
  arXiv  Detail & Related papers  (2025-06-26T16:45:20Z)
• A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions [8.717610965852037]
  We propose a novel training paradigm to generate diverse responses of a given proficiency level.<n>We convert responses into synthesized speech via speaker-aware text-to-speech synthesis.<n>A multimodal large language model integrates aligned textual features with speech signals to predict proficiency scores directly.
  arXiv  Detail & Related papers  (2025-06-04T15:42:53Z)
• Harmonizing Large Language Models with Collaborative Behavioral Signals for Conversational Recommendation [20.542601754190073]
  This work presents a novel probabilistic framework that synergizes behavioral patterns with conversational interactions through latent preference modeling.<n>The framework first derives latent preference representations through established collaborative filtering techniques, then employs these representations to jointly refine both the linguistic preference expressions and behavioral patterns.
  arXiv  Detail & Related papers  (2025-03-12T09:01:09Z)
• 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)
• Yeah, Un, Oh: Continuous and Real-time Backchannel Prediction with Fine-tuning of Voice Activity Projection [24.71649541757314]
  Short backchannel utterances such as "yeah" and "oh" play a crucial role in facilitating smooth and engaging dialogue.<n>This paper proposes a novel method for real-time, continuous backchannel prediction using a fine-tuned Voice Activity Projection model.
  arXiv  Detail & Related papers  (2024-10-21T11:57:56Z)
• Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension [81.47133615169203]
  We propose compositional learning for holistic interaction across utterances beyond the sequential contextualization from PrLMs. We employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets.
  arXiv  Detail & Related papers  (2023-01-10T13:18:25Z)
• DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling [3.3578533367912025]
  We propose a framework that incorporates augmented versions of a dialogue context into the learning objective. We show that our proposed augmentation method outperforms previous data augmentation approaches.
  arXiv  Detail & Related papers  (2022-04-15T23:39:41Z)

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.