SIMULATIONUse the following login credentials as needed: To enter your username, place your cursor in the Sign in box and click on the username below. To enter your password, place your cursor in the Enter password box and click on the password below. Azure Username: admin@abc.com Azure Password: XXXXXXXXXXXX The following information is for technical support purposes only:Lab Instance: 12345678TaskYou need to create a version of the 1u12345678 Language Understanding (classic) model. The new version must have a version name of 1.0 and must be active. To complete this task, sign in to the Language Understanding portal at https://www.luis.ai/.
Answer(s): A
Step 1: Clone a version1. Select the version you want to clone (1u12345678) then select Clone from the toolbar.2. In the Clone version dialog box, type a name for the new version. Type 1.0Step 2: Set active versionSelect a version from the list, then select Activate from the toolbar.
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-manage-versions
You have a Language service resource that performs the following: •Sentiment analysis •Named Entity Recognition (NER) •Personally Identifiable Information (PII) identification You need to prevent the resource from persisting input data once the data is analyzed. Which query parameter in the Language service API should you configure?
Answer(s): D
How is data retained and what customer controls are available?Data sent in synchronous or asynchronous calls may be temporarily stored by Azure Cognitive Service for language for up to 48 hours only and is purged thereafter. This data is encrypted and is only accessible to authorized on call engineers when service support is needed for debugging purposes in the event of a catastrophic failure. To prevent this temporary storage of input data, the LoggingOptOut query parameter can be set accordingly. By default, this parameter is set to false for Language Detection, Key Phrase Extraction, Sentiment Analysis and Named Entity Recognition endpoints. The LoggingOptOut parameter is true by default for the PII and health feature endpoints. More information on the LoggingOptOut query parameter is available in the API reference.
https://learn.microsoft.com/en-us/legal/cognitive-services/language-service/data-privacy
You have an Azure Cognitive Services model named Model1 that identifies the intent of text input.You develop an app in C# named App1.You need to configure App1 to use Model1.Which package should you add to App1?
Answer(s): C
https://learn.microsoft.com/en-us/dotnet/api/overview/azure/ai.language.conversations-readme?view=azure-dotnet
HOTSPOT (Drag and Drop is not supported)You are building content for a video training solution.You need to create narration to accompany the video content. The solution must use Custom Neural Voice.What should you use to create a custom neural voice, and which service should you use to generate the narration? To answer, select the appropriate options in the answer area.NOTE: Each correct answer is worth one point.
Box 1: The Speech Studio portalCustom Neural VoiceHere's an overview of the steps to create a custom neural voice in Speech Studio:1. Create a project to contain your data, voice models, tests, and endpoints.2. Set up voice talent.3. Prepare training data in the right format.4. Train your voice model. 5. Test your voice.6. Deploy and use your voice model in your apps.Box 2: Text-to-speechNarrationNeural text-to-speech voice models are trained by using deep neural networks based on the recording samples of human voices.Note: Components sequenceCustom Neural Voice consists of three major components: the text analyzer, the neural acoustic model, and the neural vocoder. To generate natural synthetic speech from text, text is first input into the text analyzer, which provides output in the form of phoneme sequence. A phoneme is a basic unit of sound that distinguishes one word from another in a particular language. A sequence of phonemes defines the pronunciations of the words provided in the text.Next, the phoneme sequence goes into the neural acoustic model to predict acoustic features that define speech signals. Acoustic features include the timbre, the speaking style, speed, intonations, and stress patterns. Finally, the neural vocoder converts the acoustic features into audible waves, so that synthetic speech is generated.
https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/custom-neural-voice
HOTSPOT (Drag and Drop is not supported)You are building a call handling system that will receive calls from French-speaking and German-speaking callers. The system must perform the following tasks:•Capture inbound voice messages as text.•Replay messages in English on demand.Which Azure Cognitive Services services should you use? To answer, select the appropriate options in the answer area.NOTE: Each correct selection is worth one point.
Box 1: Speech-to-textSpeech to text quickly and accurately transcribes audio to text in more than 100 languages and variants.Box 2: Text-to-speech and TranslatorMicrosoft Translator is a multilingual machine translation cloud service provided by Microsoft.Microsoft Translator also offers text and speech translation through cloud services for businesses. Service for text translation via the Translator Text API ranges from a free tier supporting two million characters per month to paid tiers supporting billions of characters per month
https://azure.microsoft.com/en-us/products/cognitive-services/speech-to-text/https://en.wikipedia.org/wiki/Microsoft_Translator
Post your Comments and Discuss Microsoft AI-102 exam prep with other Community members:
Our website is free, but we have to fight against AI bots and content theft. We're sorry for the inconvenience caused by these security measures. You can access the rest of the AI-102 content, but please register or login to continue.