Which type of data is used to train a Custom Speech model to recognize domain-specific terms?

Text data with example sentences

What is the purpose of Custom Speech in Azure Speech?

To translate speech between custom language pairs

To create custom intents for speech recognition

To generate custom voices for text-to-speech

To improve speech recognition accuracy for specific vocabulary, accents, or audio conditions

A mobile app reads news articles aloud. Users want the app to pause longer between paragraphs and emphasize the headline. You need to modify the SSML sent to Azure Speech. What should you do?

Add between paragraphs and around the headline.

Use to adjust the pronunciation of the headline words.

Add for the entire article and for the headline.

Use with style='news' for the whole article.

A smart speaker application needs to respond only when the user says 'Hey Device' followed by a command. The device is always listening, but the application should not process any other speech until the wake word is detected. What should the developer configure?

Use Intent Recognition with a pattern matching rule for 'Hey Device'.

Use Speech Translation to detect when the user says 'Hey Device' in another language.

Run continuous Speech-to-Text recognition and filter the transcript for the phrase 'Hey Device'.

Use the Speech SDK's KeywordRecognizer with a custom keyword model for 'Hey Device'.

Microsoft Certified:Azure AI Engineer Associate

Domain 5Objective 2

Process and Translate Speech AI-102 Practice Questions (Page 4)

Part of the Implement natural language processing solutions domain, which accounts for 15-20% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~6–13 in this domain), expect 2–4 from this objective — we provide 45 practice questions to prepare you well beyond it. (estimate)

45questions here

9free pages

9concepts

15-20%of the exam

Questions 16–20

16foundation · easy
Which type of data is used to train a Custom Speech model to recognize domain-specific terms?
Select an answer first
17foundation · easy
What is the purpose of Custom Speech in Azure Speech?
Select an answer first
18foundation · easy
Which Azure Speech feature would you use to provide real-time subtitles in a different language for a live presentation?
Select an answer first
19application · medium
A mobile app reads news articles aloud. Users want the app to pause longer between paragraphs and emphasize the headline. You need to modify the SSML sent to Azure Speech. What should you do?
Select an answer first
20application · medium
A smart speaker application needs to respond only when the user says 'Hey Device' followed by a command. The device is always listening, but the application should not process any other speech until the wake word is detected. What should the developer configure?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AI-102

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AI-102” is a trademark of its owner, used for identification only.