Master the use of Azure SSML’s “Style” attribute to create emotionally engaging voice assistants. Enhance customer support with cheerful, empathetic, and calming voice tones in your AI applications.
Table of Contents
Question
Your organization, Xerigon Corporation, is developing an application that will be used for providing customer support to the end customers. You are using Azure AI Speech for the text-to-speech functionality. The application will use a voice assistant to provide automated voice support. You want to optimize the voice to express cheerfulness, empathy, and calmness.
Which of the following Speech Synthesis Markup Language (SSML) attributes should you use in this scenario?
A. effect
B. Style
C. Pitch
D. Styledegree
Answer
B. Style
Explanation
You would use the Style SSML attribute in the given scenario. The style attribute is designed to modify the speaking style of the synthesized voice. Azure AI Speech provides several predefined speaking styles, including “cheerful,” “empathetic,” and “calm,” that can be used to express specific emotions or tones. This attribute is particularly useful when you want the voice assistant to convey a specific emotion in customer support scenarios. Below is an XML example:
<voice name="en-US-JennyNeural"> <mstts:express-as style="cheerful">Thank you for calling our support line! How can I assist you today?</mstts:express-as> </voice>
You would not use the pitch SSML attribute in the given scenario. The pitch attribute controls the tone of the synthesized voice, from high to low. It is not designed to express emotions such as cheerfulness or empathy. Pitch adjustments are more about altering the frequency of the voice rather than conveying emotional styles.
You would not use the styledegree SSML attribute in the given scenario. The styledegree attribute is used in conjunction with the style attribute to adjust the intensity of the speaking style. For example, you can set the style degree to make the cheerful or empathetic tone more subtle or more pronounced. However, by itself, styledegree does not define the emotion or style, it only modifies the intensity of the applied style.
You would not use the effect SSML attribute in the given scenario. The effect attribute is used to apply special audio effects to the synthesized speech, such as adding an echo or reverberation. These effects can alter the sound of the voice but are not intended to convey emotions or speaking styles such as cheerfulness or empathy.
Microsoft Azure AI Engineer Associate AI-102 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Engineer Associate AI-102 exam and earn Microsoft Azure AI Engineer Associate AI-102 certification.