The limits of speech recognition
The limits of speech recognition
复制标题
语音识别的局限性
DOI：
--
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
B. Shneiderman
中科院分区：
文献类型：
--
作者：
B. Shneiderman
通过了解人类听觉记忆和处理的认知过程，界面设计师可以更有效地整合语音，更成功地引导用户。然后，通过欣赏HHI和HCI之间的差异，设计人员可能能够选择适当的应用程序，人类使用的语音与计算机。主要的区别可能是韵律所传达的丰富的情感内容--口语中的节奏、语调和幅度。韵律对HHI是有效的，但对HCI可能是破坏性的。首先，让我们考虑人类的声音记忆和处理。短期记忆和工作记忆有时被称为听觉记忆或言语记忆。人类大脑中暂时保存大量信息并解决问题的部分也支持说话和倾听。因此，解决坚韧最好在安静的环境中进行，不要说话或听别人说话。然而，身体活动是由大脑的另一部分处理的，因此解决问题与日常身体活动（如步行或驾驶）是相容的。简而言之，人类可以很容易地说话和走路，但他们发现说话和思考更难。同样，当操作计算机时，大多数人可以打字（或移动鼠标）和思考，但他们发现说话和思考更难。手眼协调是在不同的大脑结构中完成的，因此打字或鼠标移动可以与解决问题并行进行。
By understanding the cognitive processes surrounding human acoustic memory and processing, interface designers may be able to integrate speech more effectively and guide users more successfully. Then by appreciating the differences between HHI and HCI designers may be able to choose appropriate applications for human use of speech with computers. The key distinction may be the rich emotional content conveyed by prosody -- the pacing, intonation, and amplitude in spoken language. Prosody is potent for HHI, but may be disruptive for HCI. First let’s consider human acoustic memory and processing. Short-term and working memory is sometimes called acoustic or verbal memory. The part of the human brain that transiently holds chunks of information and solves problems also supports speaking and listening. Therefore working on a tough problem is best done in quiet environments; without speaking or listening to someone. However, physical activity is handled in another part of the brain so problem solving is compatible with routine physical activities such as walking or driving. In short, humans can easily speak and walk, but they find it harder to speak and think. Similarly when operating a computer, most humans can type (or move a mouse) and think, but they find it harder to speak and think. Hand-eye coordination is accomplished in different brain structures so typing or mouse movement can be done in parallel with problem solving.