AI-102 Question #421: Real Exam Question with Answer & Explanation

Question

Drag and Drop Question You are building a phone call handling solution that will use the Azure AI Speech service and a custom neural voice. You need to create a custom speech model. Which five actions should you perform in sequence from Speech Studio? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. Answer:

Options

• 1Create a custom voice project.
• 2Upload a consent statement for the voice talent as a WAV file.
• 3Upload speech samples as MP3 files.
• 4Train the model by using a neural training method.
• 5Analyze the quality of the audio data and resolve identified issues.

Explanation

To create a custom neural voice in Azure AI Speech Studio, you must follow a specific sequence: first create a custom voice project to establish the workspace, then upload a consent statement as a WAV file (legally required to confirm the voice talent consents to their voice being used), upload speech samples as MP3 files (the training data), analyze the audio quality and resolve issues to ensure clean training data, and finally train the model using a neural training method. This sequence ensures legal compliance, proper data ingestion, quality validation, and successful model training in the correct dependency order.

No community discussion yet for this question.