arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.22374cs.HC
收藏

VoiceAlign:一种增强传统语音用户界面系统可用性的 shim 层

VoiceAlign: A Shimming Layer for Enhancing the Usability of Legacy Voice User Interface Systems

Pennsylvania State University(宾夕法尼亚州立大学)

Md Ehtesham-Ul-Haque, Syed Masum Billah

AI总结:

VoiceAlign 通过适应性 shim 层提升传统语音用户界面系统的可用性,减少命令失败并降低用户认知负担。

摘要:

语音用户界面(VUIs)正迅速从辅助功能转变为主流交互方式。然而,尽管大多数操作系统内置的语音命令具备强大的技术能力,但它们仍然未被充分利用。通过分析四个商业 VUI 系统和与 16 名参与者进行的形成性研究,我们发现固定命令格式需要精确的措辞,限制性的超时机制在规划暂停期间丢弃输入,而不足的反馈会阻碍多步骤交互。为了解决这些挑战,我们开发了 VoiceAlign,一种适应性的 shim 层,用于在用户和传统 VUI 系统之间进行中介。VoiceAlign 截获自然语音命令,将其转换为所需的语法格式,使用大型语言模型,并通过一个透明于底层系统的虚拟音频通道传输这些调整后的命令。在与 12 名参与者进行的评估中,VoiceAlign 将命令失败率减少了一半,每个任务所需的命令数量减少了 25%,并且在与现有传统 VUI 系统配合时显著降低了认知和时间需求。此外,我们创建了一个由我们的研究启发的合成数据集,并微调了一个小型语言模型,该模型在本地服务时能够以 200 毫秒的响应时间实现超过 90% 的准确率,消除了对第三方 API 的依赖,同时在边缘设备上实现了实时交互。这项工作展示了现代 AI 技术如何解锁未被充分利用的传统 VUI 系统的潜力,而无需要求系统修改,提供了一个实用的解决方案,而无需替换现有的基础设施。

英文摘要:

Voice user interfaces (VUIs) are rapidly transitioning from accessibility features to mainstream interaction modalities. Yet most operating systems' built-in voice commands remain underutilized despite possessing robust technical capabilities. Through our analysis of four commercial VUI systems and a formative study with 16 participants, we found that fixed command formats require exact phrasing, restrictive timeout mechanisms discard input during planning pauses, and insufficient feedback hampers multi-step interactions. To address these challenges, we developed VoiceAlign, an adaptive shimming layer that mediates between users and legacy VUI systems. VoiceAlign intercepts natural voice commands, transforms them to match the required syntax using a large language model, and transmits these adapted commands through a virtual audio channel that remains transparent to the underlying system. In our evaluation with 12 participants, VoiceAlign reduced command failures by half, required 25% fewer commands per task, and significantly lowered cognitive and temporal demands when paired with an existing legacy VUI system. Furthermore, we created a synthetic dataset informed by our studies and fine-tuned a small language model that achieves over 90% accuracy with 200 ms response time when served locally, eliminating dependence on third-party APIs while enabling real-time interaction on edge devices. This work demonstrates how modern AI techniques can unlock the underutilized potential of legacy VUI systems without requiring system modifications, offering a practical solution without replacing existing infrastructure.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑