Do you want me to send you the whole 24 questions was on the test and tell you which topics they said we got it wrong? I can try to put it here. If not I can email it to you.
Here is the 24 questions with my answers.
2/20/2022
Question 1 of 24
You have a Speech service resource.
You need to develop an application that creates real-time captions for audio.
What should you include in the code?
Select only one answer.
1. SpeakerRecognizer
2. KeywordRecognizer
3. SpeechRecognizer
4. SpeechSynthesizer
My Answer is "3. SpeechRecognizer"
Question 2 of 24
You have an application that performs Speech to Text services for users by using the Speech SDK.
You need to add the ability to perform Text to Speech in the application.
Besides the text, which other values should you include in your queries?
1. the pronunciation
2. the voice
3. keyword
4. the phrase list
My answer was 1. The Pronunciation
Question 3 of 24
You are building a text to speech solution.
You need to ensure that your solution supports different name pronunciations.
What Speech Synthesis Markup Language (SSML) element should you use?
1. phoneme
2. mstts:express-as
3.break
4. lang
My answer was 1. Phoneme
Question 4 of 24
You develop an application by using the Speech SDK. The application translates the English language version of podcasts into French and German.
You need to create the code to provide the English version of the podcast for translation.
Which two objects should you add to the code?
Select all answers that apply.
1. TranslationRecognizer
2. SpeechRecognizer
3. SpeechSynthesizer
4. AutoDetect SourceLanguageConfig
5. SpeechTranslationConfig
My answer is 2. SpeechRecognizer
Question 5 of 24
You have a Azure Video Analyzer for Media service that provides a search interface for video content.
You need to extract what is said in the videos so that it can be translated into other languages.
What should you extract?
1. labels
2. brands
3. transcripts
4. keywords
The answer is 3. Transcripts
Question 6 of 24
You build an application that uses Language Understanding.
You need to ensure that the application support speech inputs by using the Speech service.
What should you configure for Language Understanding?
1. Enable the Speech priming setting during model publishing.
2. Add additional utterances to the intents in the model before publishing.
3. Set the endpoint URL parameter verbose to true.
4. Enable the Normalize punctuation setting on the application.
Answer: 1. Enable the Speech priming setting during model publishing.
Question 7 of 24
You plan to use a Language Understanding container for an application that you previously exported.
Which two values from the underlying Language Understanding resource should you retrieve before you can containerize the application?
1. the subscription key
2. the endpoint URI
3. the prediction key
4. the resource location
My Answer: 2. the endpoint URI
Question 8 of 24
You make a Text Analytics API call.
You call the following URL.
You send the following body.
{
"documents": [
"id": "1",
"countryHint":"US",
"text": "We analyzed text to see what would happen"
},
"id": "2",
"countryHint":"UK",
"text": "We analysed text to see what would happen"
]
}
You receive the following response.
"statistics": {
"documentsCount": 2,
"validDocumentsCount": 1,
"erroneousDocumentsCount": 1,
"transactionsCount": 1
"documents": [{
"detectedLanguages": [{
"name": "English",
"iso6391Name": "en",
"score": 1.0
}],
"charactersCount": 41,
"errors": [{
"message": "Country hint is not valid. Please specify an ISO 3166-1 alpha-2 two letter country code."
}]
Which three of the following statements correctly describe the code?
1. The text fragment that has ID 1 is identified as English.
2. US is a valid value for countryHint.
3. The document that has countryHint=UK does not generate a billable transaction.
4. UK is a valid value for name.
5. The document that has countryHint=US does not generate a billable transaction.
My answer: 1. The text fragment that has ID 1 is identified as English.
Question 9 of 24
You plan to use Text Analytics to detect the language of reviews.
You need to route the reviews that are multi-lingual to a human translator.
Which field in the JSON response should you use to filter records?
1. score
2. errors
3. statistics
4. name
My answer: 3. statistics
Question 10 of 24
You develop a product review feature for an international e-commerce application.
When reviews are received by the application, the application posts the reviews to an Azure Cosmos DB database.
You need to develop an Azure Function that uses the Text Analytics API to notify a team when a negative review is posted. The notification must be sent as quickly as possible.
Which two components should you use in the function to identify a negative review?
1. the Sentiment endpoint
2. an Azure Cosmos DB trigger
3. a schedule triggert
4. he Key Phrase endpoint
5.the Detect Language endpoint
6.an Azure Cosmos DB output
My answer: 1. the Sentiment endpoint
Question 11 of 24
"language": "en",
"text": "Our tour guide took us up the Space Needle during our trip to Seattle last week."
You receive the following response body.
"documentsCount": 1,
"erroneousDocumentsCount": 0,
"score": 0.5,
"charactersCount": 80,
"errors": []
The text fragment that has ID 1 contains 80 alphanumeric characters.
Select Yes if the statement is true. Otherwise, select No.
1. Yes
2. No
My answer is Yes
Question 12 of 24
You are designing a chatbot for a restaurant.
You plan to include a series of questions that will be required to complete a reservation.
What type of dialog should you use?
1. Waterfall
2. Prompt
3. QnA Maker
4. Action
My answer was Prompt ( I know you said Qna Maker)
Question 13 of 24
You are building a chatbot by using the Microsoft Bot Framework Composer.
The chatbot will include a dialog that will be used to enter prices of products.
Users will perform an action for the products.
The products and prices will resemble the following:
Which type of recognizer should you use?
1. Regex
2. None
3. LUIS
My answer was 3. LUIS
Question 14 of 24
You are building a chatbot that uses the Bot Framework Composer.
You need to collect user contact information.
What should you use to validate the user phone numbers?
1. Language Generator
2. Recognizer
3. Trigger
4. Dialog
My answer is 2. Recognizer
Question 15 of 24
You need to test the bot.
What two tools could you use?
1. Bot Framework CLI
2. Bot Framework Composer
3. Bot Framework SDK
4. Bot Framework Emulator
My answer is
Question 16 of 24
You are building an Azure Cognitive Search solution.
What should you use to increase the amount of concurrent query requests that can be handled by the solution?
1. Replicas
2. Partitions
3. Indexes
4. Pricing tier
My answers 4. Pricing Tier
Question 17 of 24
You have 20,000 PDF documents that must be indexed by using Azure Cognitive Search.
You need to recommend a storage solution for the PDFs.
What should you recommend?
1. Azure Storage
2. Microsoft SQL Server
3. Azure Cosmos DB
4. Amazon AWS S3
My answer is s1. Azure Storage
Question 18 of 24
You are defining an index for blog posts.
Searches must query the description field and return the descriptions in search results.
What field options should you select for the description field?
1. Retrievable and Searchable
2. Filterable and Searchable
3. Retrievable and Sortable
4. Facetable and Sortable
My answer is 2. Filterable and Searchable
Question 19 of 24
You plan to build an API for a custom skillset.
What data format should you use for the API to accept and return?
1. JSON
2. XML
3. YAML
4. HTML
My answer is 1. JSON
Question 20 of 24
You plan to build an Azure Cognitive Search solution that will search images and PDF documents.
Users of the solution will search for text, captions, key phrases, identified objects, or named entities.
Each day, you will need to index and enrich 5,000 images and 10,000 PDFs.
Which type of resource should you create for the planned solution?
1. Computer Vision
2. Text Analytics
3. Azure Machine Learning
4.Azure Cognitive Services
My Answer is 1. Computer Vision
Question 21 of 24
You have an Azure Cognitive Search solution.
You need to extract text from PDFs during indexing.
Which skill should you use?
1. key phrase extraction
2. content moderation
3. sentiment
4. optical character recognition (OCR)
My Answer is :. optical character recognition (OCR)
Question 22 of 24
You have a custom skillset that receives a complex set of fields in a response.
What should you use to simplify and restructure the fields?
1. A shaper skill
2. An object projection
3. An indexer
4. A data source
My answer is A. A shaper skill
Question 23 of 24
You have an enrichment pipeline that uses Azure Cognitive Search.
The pipeline ingests Azure Cosmos DB data and identifies key phrases.
The application that generates the data must be able to retrieve key phrases and confidence by querying an API.
What should you use to persist the data?
1. a table store
2. a file storea
3.an object store
The correct answer is 3. an Object store
Question 24 of 24
You have an enrichment pipeline in Azure Cognitive Services.
The enrichment pipeline has a custom skill that calls an API.
You need to ensure that all responses from the API are structured consistently.
Which skill should you add to the skillset?
1. Merge
2. Shaper
3. ConditionalText
4. Split
My answer is 2. Shaper
I would appreciate if you can help me to get this over. I need 65% to pass and i only got 45%.
Here is what parts I am wrong.
You are developing a Text to Speech application by using the Speech service.
The application will be used to convert interview transcripts into audio files.
You need to ensure that the audio files can support multiple speaker voices.
What should you use?
1.HTML
2.neural voices
3. SSML
4. the Long Audio API