exam questions

Exam AI-102 All Questions

View all questions & answers for the AI-102 exam

Exam AI-102 topic 10 question 2 discussion

Actual exam question from Microsoft's AI-102
Question #: 2
Topic #: 12
[All AI-102 Questions]

You are developing the knowledgebase.
You use Azure Video Analyzer for Media (previously Video indexer) to obtain transcripts of webinars.
You need to ensure that the solution meets the knowledgebase requirements.
What should you do?

  • A. Create a custom language model
  • B. Configure audio indexing for videos only
  • C. Enable multi-language detection for videos
  • D. Build a custom Person model for webinar presenters
Show Suggested Answer Hide Answer
Suggested Answer: A 🗳️

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
james2033
Highly Voted 1 year, 5 months ago
Selected Answer: A
Keyword "jargon", so choose "A. Create a custom language model" .
upvoted 22 times
...
zellck
Highly Voted 1 year, 7 months ago
Selected Answer: A
A is the answer. https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-language-model-overview Azure Video Indexer supports automatic speech recognition through integration with the Microsoft Custom Speech Service. You can customize the Language model by uploading adaptation text, namely text from the domain whose vocabulary you'd like the engine to adapt to. Once you train your model, new words appearing in the adaptation text will be recognized, assuming default pronunciation, and the Language model will learn new probable sequences of words.
upvoted 12 times
zellck
1 year, 7 months ago
Gotten this in Jul 2023 exam.
upvoted 6 times
...
evangelist
1 year ago
the correct choice between Stream and string depends on the source of the image: If you have the image file and want to upload it directly from the client or server where the request is being made, you should use a Stream. This approach is direct and efficient for handling binary data without the need for encoding or hosting the image externally. If the image is already hosted online and accessible via a URL, you use a string containing the URL to let the API fetch the image for analysis.
upvoted 1 times
...
...
syupwsh
Most Recent 1 day, 2 hours ago
Selected Answer: A
Create a custom language model is CORRECT because this feature ensures that the solution can transcribe accounting jargon with high accuracy. This directly aligns with the knowledgebase requirement to support transcription of specialized terminology, such as accounting-specific jargon, which cannot be achieved with generic models or basic audio indexing. A custom language model allows training on domain-specific terminology, improving transcription quality. A is correct
upvoted 1 times
...
JuneRain
5 months, 4 weeks ago
This question was in the test I took on August 2024
upvoted 3 times
...
nanaw770
8 months ago
Selected Answer: A
Sorry, A is the correct answer.
upvoted 1 times
...
nanaw770
8 months ago
Selected Answer: B
B is the correct answer.
upvoted 1 times
...
takaimomoGcup
8 months, 3 weeks ago
Is this question still available on May 21, 2024?
upvoted 1 times
...
NullVoider_0
10 months, 1 week ago
Question is incomplete and needs more context to determine the answer.
upvoted 2 times
...
evangelist
1 year ago
Selected Answer: A
A. Create a custom language model: This option allows for the customization of the language model used for transcribing audio and video content. By creating a custom language model, you can train it to understand and transcribe specialized jargon and industry-specific terminology with high accuracy. This directly addresses the requirement to transcribe jargon with high accuracy and supports searches for equivalent terms by ensuring that the transcriptions are as accurate and relevant as possible.
upvoted 2 times
...
rdemontis
1 year, 2 months ago
Selected Answer: A
A is the answer. We need to support jargon. https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-language-model-overview
upvoted 3 times
...
mk1967
2 years, 5 months ago
Selected Answer: A
The requirement "Can transcribe jargon with high accuracy" wouldn't be met with the answer B.
upvoted 3 times
...
AjoseO
2 years, 6 months ago
Selected Answer: A
--- Can transcribe jargon with high accuracy Video Indexer (VI), the AI service for Azure Media Services enables the customization of language models by allowing customers to upload examples of sentences or words belonging to the vocabulary of their specific use case. Since speech recognition can sometimes be tricky, VI enables you to train and adapt the models for your specific domain. Harnessing this capability allows organizations to improve the accuracy of the Video Indexer generated transcriptions in their accounts. https://azure.microsoft.com/en-us/blog/new-ways-to-train-custom-language-models-effortlessly/
upvoted 3 times
...
Eltooth
2 years, 6 months ago
Selected Answer: A
Leaning towards A on this. https://azure.microsoft.com/en-us/blog/new-ways-to-train-custom-language-models-effortlessly/ https://docs.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-overview
upvoted 1 times
...
AiEngineerS
2 years, 7 months ago
I think this is B... because even A makes sense... but u have to extract this information from video somehow. So B
upvoted 1 times
...
ANIKI51419
2 years, 8 months ago
should be A
upvoted 3 times
sdokmak
2 years, 7 months ago
I think you're right https://azure.microsoft.com/en-us/blog/new-ways-to-train-custom-language-models-effortlessly/
upvoted 2 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
Loading ...
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago