Building Speech-Enabled Applications

What information do you need from the Speech resource to use it from a client application through one of the supported SDKs?

• Location

• Key

• Subscription ID

• Unique Resource ID

When using the text-to-speech feature of the Speech service, where do the voices come from?

• You have to provide the voices by recording a library of words and sounds.

• Azure provides one voice that everyone can use.

• Azure provides synthetic and more natural sounding voices for you to choose from

• You can to link a Voice service to the text-to-speech application to use any of Azure’s voices.

What do you need to use to specify the characteristics of speech produced by the Speech SDK?

• Speech characteristics cannot be specified

• Speech characteristics are randomized

• Parameters that specify emotion

• Speech Synthesis Markup Language

Which setting should you specify if you want to translate speech from an audio file to text?

• AudioConfig

• SpeechConfig

• SpeechTranslationConfig

• TranslationRecognizer

The speech-to-text API can perform speech recognition on which of the following types of audio?

• Short streams of audio (up to 60 seconds)

• Long streams of audio

• Batches of audio files

• Audio that is at least 60 seconds

Lusukama wants to create a speech-based help desk for English and Spanish patrons but only have English speaking customer service employees. Describe how you would help them with this using Azure Cognitive Services.

Which API would be best to use if you were creating an interactive speech application for short questions and answers, and why?

Customers often appreciate when synthesized voices are not only localized to language but also sound realistic and have a similar accent to themselves. How would you accomplish this using the Speech SDK?

What feature of the Speech SDK would enable you to create the following spoken dialog between two neural voices and how? Ariana (cheerfully): "I say tomato: Guy: "I say tomato (pronounced tom-ah-toe) ... Let's call the whole thing off!

You are building a single application that can allow two people who speak different languages to speak to each other, can you use the Synthesizing event? Why or why not?