AI-900 Question 237
Select 2A company wants to develop a voice-controlled virtual assistant using Azure AI Speech services. They need the assistant to recognize spoken commands, convert them into text, and also respond to users by converting text responses into speech. Which capabilities of the Azure AI Speech service should they use?
- A
Speech-to-Text
- B
Text-to-Speech
- C
Speech Translation
- D
Speaker Recognition
Show answer and explanation
Correct answers: A, B
Explanation
The Azure AI Speech service provides Speech-to-Text for converting spoken language into text and Text-to-Speech for generating spoken responses from text. These two capabilities are fundamental for building a voice-controlled virtual assistant. Other features like Speech Translation and Speaker Recognition are useful in specific cases, but they are not required for this scenario.
- A. Correct.
Speech-to-Text is used to convert spoken commands into textual data, which is essential for processing user input in a voice-controlled virtual assistant.
- B. Correct.
Text-to-Speech is used to convert the assistant's textual responses into spoken words, enabling the assistant to communicate verbally.
- C. Incorrect.
Speech Translation is used for real-time translation of spoken language into another language, which is not a requirement in this scenario.
- D. Incorrect.
Speaker Recognition identifies or verifies the identity of a speaker, which is not directly relevant to recognizing commands or generating responses in this scenario.