Research Papers 论文研究 7h ago Updated 2h ago 更新于 2小时前 43

AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking AVERT:音频验证裁决用于口语对话状态追踪

AVERT introduces an audio-verified adjudication framework for spoken dialogue state tracking that corrects ASR errors without retraining base models Three targeted operators—vote, add, and swap—address inconsistent cross-turn values, omitted slots, and audio-inconsistent predictions respectively On SpokenWOZ, AVERT achieves 40.13 JGA, outperforming both a base speech-LLM (33.04) and a text-only editor (38.34), matching a 1B end-to-end system (39.32) The audio-conditioned verifier provides a stat 提出AVERT方法,通过音频验证和跨轮次一致性解决口语对话状态追踪中的ASR错误 设计三个操作符(vote、add、swap)分别处理不一致值、遗漏槽位和音频不支持的值 在SpokenWOZ基准上达到40.13 JGA,超越文本编辑器(38.34)且接近端到端系统(39.32) 无需重新训练基础模型,仅使用两个1B解码器即可实现显著性能提升 限制操作符到特定槽位子集是关键设计,防止覆盖正确的分类值

58
Hot 热度
72
Quality 质量
55
Impact 影响力

Analysis 深度分析

TL;DR

  • AVERT introduces an audio-verified adjudication framework for spoken dialogue state tracking that corrects ASR errors without retraining base models
  • Three targeted operators—vote, add, and swap—address inconsistent cross-turn values, omitted slots, and audio-inconsistent predictions respectively
  • On SpokenWOZ, AVERT achieves 40.13 JGA, outperforming both a base speech-LLM (33.04) and a text-only editor (38.34), matching a 1B end-to-end system (39.32)
  • The audio-conditioned verifier provides a statistically significant gain, and restricting operators to error-prone slot subsets prevents overwriting correct categorical values

Why It Matters

Spoken dialogue systems remain bottlenecked by ASR errors that propagate across conversation turns, and this work demonstrates that post-hoc adjudication with audio verification can close a significant performance gap without expensive retraining. For practitioners building conversational AI, AVERT offers a plug-and-play improvement layer that approaches end-to-end system performance using modular components, making it a practical pathway for incremental deployment.

Technical Details

  • AVERT operates as a post-processing adjudication layer on top of existing speech-LLM outputs, combining cross-turn agreement scoring with a trained audio-conditioned verifier to evaluate candidate slot values
  • Three error-specific operators are deployed: "vote" resolves values predicted inconsistently across turns, "add" recovers omitted slots, and "swap" corrects values unsupported by the audio signal
  • Each operator is restricted to a selected subset of slots where its corresponding error type is most common, preventing unintended overwrites of correct categorical values
  • Evaluated on SpokenWOZ, AVERT uses two 1B-parameter decoders and achieves 40.13 JGA compared to 33.04 for the base speech-LLM and 38.34 for a text-only editor, without any retraining of the underlying models

Industry Insight

  • Modular adjudication layers like AVERT provide a cost-effective alternative to training massive end-to-end spoken dialogue systems, enabling teams to incrementally improve existing pipelines without full retraining
  • The finding that operator restriction to error-prone slot subsets is critical suggests that future systems should incorporate error-profile-aware gating rather than applying corrections uniformly across all slots
  • Audio-verified correction represents a broader paradigm shift: rather than treating ASR errors as irrecoverable noise, spoken dialogue systems can leverage raw audio signals as an independent verification source to resolve ambiguities that text-only approaches cannot

TL;DR

  • 提出AVERT方法,通过音频验证和跨轮次一致性解决口语对话状态追踪中的ASR错误
  • 设计三个操作符(vote、add、swap)分别处理不一致值、遗漏槽位和音频不支持的值
  • 在SpokenWOZ基准上达到40.13 JGA,超越文本编辑器(38.34)且接近端到端系统(39.32)
  • 无需重新训练基础模型,仅使用两个1B解码器即可实现显著性能提升
  • 限制操作符到特定槽位子集是关键设计,防止覆盖正确的分类值

为什么值得看

本文针对口语对话系统中ASR错误持久化问题提出了一种高效的纠错框架,为对话状态追踪提供了新的解决思路。其无需重训练即可显著提升性能的特点,对实际部署具有直接应用价值。

技术解析

  • ASR错误主要集中在实体值上且跨轮次持续存在,使对话状态追踪同时成为生成问题和编辑问题
  • AVERT通过结合跨轮次一致性与训练的音频条件验证器来评分候选值,并使用三个受限操作符解决三类可恢复错误
  • 在SpokenWOZ基准测试中,基础语音LLM达到33.04 JGA,文本编辑器提升至38.34,AVERT达到40.13,无需重新训练任一模型
  • 音频验证器贡献了统计显著的性能提升,且限制操作符到选定槽位子集至关重要:移除该限制会导致无限制投票覆盖正确的分类值,性能反而低于编辑器

行业启示

  • 口语对话系统可借鉴"生成+编辑"的分阶段架构,在保持端到端系统简洁性的同时提升纠错能力
  • 音频验证机制为多模态对话系统提供了新的研究方向,值得在更多语音交互场景中探索
  • 无需重训练的即插即用纠错方案降低了部署成本,为现有系统的性能优化提供了实用路径

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Speech 语音 Conversational AI 对话系统 Research 科学研究 Evaluation 评测