Google Exam Professional Machine Learning Engineer Topic 2 Question 95 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam

Question #: 95
Topic #: 2

[All Professional Machine Learning Engineer Questions]

You work at an organization that maintains a cloud-based communication platform that integrates conventional chat, voice, and video conferencing into one platform. The audio recordings are stored in Cloud Storage. All recordings have an 8 kHz sample rate and are more than one minute long. You need to implement a new feature in the platform that will automatically transcribe voice call recordings into a text for future applications, such as call summarization and sentiment analysis. How should you implement the voice call transcription feature following Google-recommended best practices?

AUse the original audio sampling rate, and transcribe the audio by using the Speech-to-Text API with synchronous recognition.

BUse the original audio sampling rate, and transcribe the audio by using the Speech-to-Text API with asynchronous recognition.

CUpsample the audio recordings to 16 kHz. and transcribe the audio by using the Speech-to-Text API with synchronous recognition.

DUpsample the audio recordings to 16 kHz. and transcribe the audio by using the Speech-to-Text API with asynchronous recognition.

Show Suggested Answer

Suggested Answer: D

by Dell at Jan 13, 2025, 09:25 PM

Limited Time Offer

25%

Off

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Willodean

24 days ago

I'm not sure. Maybe upsampling to 16 kHz could improve the transcription quality?

upvoted 0 times

...

Justine

25 days ago

I agree with Juliana. Synchronous recognition will provide real-time transcription for better accuracy.

upvoted 0 times

...

Lang

29 days ago

Wait, is this a trick question? If the recordings are more than a minute long, I bet the answer is D. Gotta love those long-winded callers, am I right?

upvoted 0 times

Cora

13 days ago

Yeah, D makes sense for longer recordings. Those callers can really go on and on.

upvoted 0 times

...

Devon

16 days ago

I think you're right, D seems like the best option for longer recordings.

upvoted 0 times

...

Juliana

29 days ago

I think we should use the original audio sampling rate and transcribe synchronously with the Speech-to-Text API.

upvoted 0 times

...

2 months ago

I think option D is the way to go. Upsampling the audio to 16 kHz and using asynchronous recognition seems like the most robust and scalable solution.

upvoted 0 times

Dulce

27 days ago

I believe option C could provide better quality results with the upsampled audio recordings.

upvoted 0 times

...

Melissa

30 days ago

I think option A might be faster since it uses the original audio sampling rate.

upvoted 0 times

...

Tamie

1 months ago

I agree, option D seems like the best choice for accurate transcription.

upvoted 0 times

...