首頁Home › 人工智慧與新興科技 AI & Emerging Tech
語音介面
1這是什麼What is it?
語音介面(VUI)以語音作為輸入與輸出的人機互動方式,如 Siri(2011)、Alexa(2014)與 Google Assistant。設計核心包括對話流程、提示語、錯誤復原與沒有視覺線索時的可發現性;Grice 的合作原則(量、質、關係、方式)為對話設計的理論基礎,並涉及隱私與無障礙。
A voice user interface (VUI) uses speech as input and output for human–computer interaction, as with Siri (2011), Alexa (2014) and Google Assistant. Design core includes dialogue flow, prompts, error recovery and discoverability without visual cues, Grice's cooperative principle (quantity, quality, relation, manner) is the theoretical basis of dialogue design, and it involves privacy and accessibility.
2常被用在哪種研究問題Typical research questions
常見問法:語音介面如何影響使用經驗?
語音介面減少視覺依賴,但缺乏視覺回饋。本研究比較有無視覺輔助的語音互動,並以任務表現與滿意度檢驗。
Voice interfaces reduce visual dependence but lack visual feedback. This study compares voice interaction with and without visual aids and tests through task performance and satisfaction.
撰寫內容,非真實研究結果,請與指導教授討論後改寫。
Written as a model example, not a real finding. Please revise with your advisor.
3怎麼測它How to measure it
可用性測試+滿意量表
Measurement notes are written in Chinese. Switch to 中/EN to read them.
4代表文獻Key references
英文論文(2000 年後)English paper (post-2000)
Clark, L., et al. (2019). The state of speech in HCI: trends, themes and challenges. Interacting with Computers, 31(4).
中文論文(2000 年後)
中文論文為預填檢索連結,請自行挑選一篇 2000 年後的期刊論文並核對作者、年份、出處後再引用。
英文引用來自模型整理,引用前請務必核對並閱讀原文。English citations are compiled by a model. Verify and read the original before citing.