Speech and Audio Services

Question 1

A media company needs to automatically generate subtitles for its videos in multiple languages. Which combination of services is the most efficient?

Accepted Answer

Amazon Transcribe to convert audio to text and Amazon Translate to translate the subtitles.

Answer

Amazon Polly to generate audio and Amazon Translate for text.

Answer

Amazon Rekognition to read lips and Amazon Comprehend to translate.

Answer

Amazon Lex to listen to the video and Amazon Connect to translate it.

Question 2

A developer wants their application to read news articles aloud with a natural intonation similar to a newscaster. Which Amazon Polly feature should they use?

Accepted Answer

Neural Text-to-Speech (NTTS) voices with 'Newscaster' style

Answer

Standard Voices

Answer

Speech Marks

Answer

Custom Lexicons

Question 3

In a meeting recording with multiple participants, which Amazon Transcribe feature allows identifying 'who spoke when' (e.g., 'Speaker 1', 'Speaker 2')?

Accepted Answer

Speaker Diarization

Answer

Channel Identification

Answer

Language Identification

Answer

Vocabulary Filtering

Question 4

A global company needs to translate technical documents containing brand-specific product names and acronyms. These terms must not be translated literally. Which Amazon Translate feature should they use?

Accepted Answer

Custom Terminology

Answer

Active Translation

Answer

Data Masking

Answer

Sentiment Analysis

Question 5

Which markup language is used in Amazon Polly to control speech aspects such as pronunciation, volume, pitch, and rate?

Accepted Answer

SSML (Speech Synthesis Markup Language)

Answer

HTML (HyperText Markup Language)

Answer

XML (Extensible Markup Language)

Answer

JSON (JavaScript Object Notation)

Question 6

A hospital wants to transcribe medical dictations containing terms like 'ibuprofen', 'hypertension', and 'cardiomyopathy'. Which service will provide the highest accuracy?

Accepted Answer

Amazon Transcribe Medical

Answer

Amazon Transcribe Standard

Answer

Amazon Comprehend Medical

Answer

Amazon Polly

Question 7

Which Amazon Transcribe feature is used to mask or remove Personally Identifiable Information (PII) like social security numbers in the output transcription?

Accepted Answer

Automatic Content Redaction

Answer

Vocabulary Filtering

Answer

Custom Vocabulary

Answer

Language Identification

Question 8

A company uses very specific domain terminology (engineering acronyms) that Amazon Transcribe does not recognize correctly. How can they improve accuracy?

Accepted Answer

Create a Custom Vocabulary and add the terms.

Answer

Use Amazon Translate to pre-process the audio.

Answer

Switch to Amazon Polly.

Answer

Use a higher quality microphone (only solution).

Question 9

A game developer wants to animate character lips to match the speech generated by Amazon Polly. Which feature should they request?

Accepted Answer

Speech Marks of type 'Viseme'

Answer

SSML <break> tags

Answer

Neural Voices

Answer

Speaker Diarization

Question 10

Which AWS service would be used to translate Word (.docx) and PowerPoint (.pptx) documents while preserving the original formatting?

Accepted Answer

Amazon Translate (Batch Document Translation)

Answer

Amazon Textract

Answer

Amazon Comprehend

Answer

Amazon Rekognition

Speech and Audio Services

A media company needs to automatically generate subtitles for its videos in multiple languages. Which combination of services is the most efficient?

Explanation

Automatic Subtitling

Official Documentation