Related papers: From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding

From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding

URL: http://arxiv.org/abs/2606.16472v1
Date: Mon, 15 Jun 2026 09:37:11 GMT
Title: From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding
Abstract summary: We propose an audio-adapted Context-Aware Decoding (CAD) approach to bridge the gap between latent context awareness and active adherence.<n>By leveraging internal attention mechanisms to isolate key historical rounds, our approach contrasts output with and without this key context during inference.<n> Evaluations on the Audio MultiChallenge benchmark demonstrate significant improvements in Semantic Memory and Self Coherence subtasks.
Score: 55.012827008735194
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Despite the success of end-to-end (E2E) spoken dialogue systems, maintaining strict context adherence in multi-round conversations remains a challenge. While prior works attribute these failures to models forgetting dialogue history, we highlight an equally critical but overlooked bottleneck: a gap between latent context awareness and active adherence. Although models internally recognize relevant past utterances, strong parametric priors often overshadow these signals during decoding. To bridge this gap, we propose an audio-adapted Context-Aware Decoding (CAD) approach. By leveraging internal attention mechanisms to isolate key historical rounds, our approach contrasts output distributions with and without this key context during inference, directly amplifying multimodal contextual signals. Evaluations on the Audio MultiChallenge benchmark demonstrate significant improvements in Semantic Memory and Self Coherence subtasks, successfully enforcing strict, context-faithful adherence.

Related papers

Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions [52.45054413627452]
TPI-Train is a dataset of 88K instances designed with speaker-aware hard negatives to enforce acoustic cue prioritization for interruption handling.<n>TPI-Bench is a comprehensive evaluation framework designed to rigorously measure the interruption-handling strategy.
arXiv Detail & Related papers (2026-04-19T10:03:42Z)
Closing the Modality Reasoning Gap for Speech Large Language Models [33.22455377292432]
TARS is a reinforcement-learning framework that aligns text-conditioned and speech-conditioned trajectories.<n>Our approach significantly narrows the modality reasoning gap and achieves state-of-the-art performance among 7B-scale Speech LLMs.
arXiv Detail & Related papers (2026-01-09T05:51:56Z)
Enhancing Dialogue Systems with Discourse-Level Understanding Using Deep Canonical Correlation Analysis [0.0]
We propose a novel framework that integrates Deep Canonical Correlation Analysis for discourse-level understanding.<n>This framework learns discourse tokens to capture relationships between utterances and their surrounding context.<n>Experiments on the Ubuntu Dialogue Corpus demonstrate significant enhancement in response selection.
arXiv Detail & Related papers (2025-04-12T06:19:08Z)
A Multi-view Discourse Framework for Integrating Semantic and Syntactic Features in Dialog Agents [0.0]
Multiturn dialogue models aim to generate human-like responses by leveraging conversational context.<n>Existing methods often neglect the interactions between these utterances or treat all of them as equally significant.<n>This paper introduces a discourse-aware framework for response selection in retrieval-based dialogue systems.
arXiv Detail & Related papers (2025-04-12T04:22:18Z)
Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems [57.16442740983528]
Crowdsourced labels play a crucial role in evaluating task-oriented dialogue systems. Previous studies suggest using only a portion of the dialogue context in the annotation process. This study investigates the influence of dialogue context on annotation quality.
arXiv Detail & Related papers (2024-04-15T17:56:39Z)
Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation [51.22712675266523]
Dialogue Topic (DTS) plays an essential role in a variety of dialogue modeling tasks. We propose a novel unsupervised DTS framework, which learns topic-aware utterance representations from unlabeled dialogue data.
arXiv Detail & Related papers (2023-05-04T11:35:23Z)
End-to-End Active Speaker Detection [58.7097258722291]
We propose an end-to-end training network where feature learning and contextual predictions are jointly learned. We also introduce intertemporal graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance.
arXiv Detail & Related papers (2022-03-27T08:55:28Z)
DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings [33.89889949577356]
We propose DialogueCSE, a dialogue-based contrastive learning approach to tackle this issue. We evaluate our model on three multi-turn dialogue datasets: the Microsoft Dialogue Corpus, the Jing Dong Dialogue Corpus, and the E-commerce Dialogue Corpus.
arXiv Detail & Related papers (2021-09-26T13:25:41Z)
Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding [53.377028000325424]
We propose an Iterative Alignment Network (IA-Net) for temporal sentence grounding task. We pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs. We also devise a calibration module following each attention module to refine the alignment knowledge.
arXiv Detail & Related papers (2021-09-14T02:08:23Z)

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