MLA-C01 Question 138
Select 2A media company wants to automate the process of generating subtitles for their video content in multiple languages and also ensure the videos are accessible to visually impaired users by describing the on-screen content. Which combination of AWS AI services should they use to achieve this?
- A
Amazon Transcribe and Amazon Translate
- B
Amazon Rekognition and Amazon Translate
- C
Amazon Rekognition and Amazon Polly
- D
Amazon Transcribe, Amazon Translate, and Amazon Rekognition
Show answer and explanation
Correct answers: A, D
Explanation
The media company needs to address two business problems: generating multilingual subtitles and making the videos accessible to visually impaired users. Amazon Transcribe and Amazon Translate can generate text-based subtitles in multiple languages. Additionally, Amazon Rekognition can analyze the visual content and, when combined with other services, can help generate descriptions of on-screen information for visually impaired users. Therefore, the correct combination is Amazon Transcribe, Amazon Translate, and Amazon Rekognition.
- A. Correct.
Amazon Transcribe can automatically convert speech in the videos into text, while Amazon Translate can translate the text into multiple languages. This combination is relevant for generating multilingual subtitles.
- B. Incorrect.
Amazon Rekognition is used for analyzing visual content, such as identifying objects or scenes, but it does not directly assist with subtitle generation. Amazon Translate is useful for translating text into multiple languages. However, this combination does not cover transcription of the video speech.
- C. Incorrect.
Amazon Rekognition can detect and analyze visual content, and Amazon Polly can convert text to speech, which may help create audio descriptions for visually impaired users. However, this combination does not address subtitle generation in multiple languages.
- D. Correct.
This combination effectively covers the requirements: Amazon Transcribe converts speech to text for subtitle generation, Amazon Translate translates subtitles into multiple languages, and Amazon Rekognition can analyze the video content to generate audio descriptions for visually impaired users.