Google Exam Professional-Machine-Learning-Engineer Topic 5 Question 86 Discussion

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

Question #: 86
Topic #: 5

[All Google 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 Raylene at Sep 12, 2024, 01:17 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

Galen

1 days ago

I see your point, Alba. Let's go with the original rate for now.

upvoted 0 times

...

Erasmo

1 days ago

I'm with the crowd on this one. Option D is the way to go. Though I do wonder if the audio quality will be as good as a human transcriptionist. Maybe we should hire some really bored linguists instead?

upvoted 0 times

...

Alba

6 days ago

That's a good point, but I think using the original rate is more efficient.

upvoted 0 times

...

Reta

7 days ago

But wouldn't upsampling to 16 kHz improve the transcription accuracy?

upvoted 0 times

...

Margurite

7 days ago

Haha, I'm just imagining the poor interns having to listen to all those long, boring call recordings. Good thing they've got the Speech-to-Text API to do the dirty work!

upvoted 0 times

...

Galen

11 days ago

I agree with Alba, using the original rate seems like the best option.

upvoted 0 times

...

Curt

13 days ago

Option D all the way! 16 kHz audio and async recognition - that's the way to go. Gotta love those Google best practices, am I right?

upvoted 0 times

...

Lai

14 days ago

I agree with Antonio. The Google-recommended best practices suggest using asynchronous recognition for longer audio files, and upsampling to 16 kHz will improve the accuracy of the transcription.

upvoted 0 times

...

Antonio

18 days ago

Option D seems like the best choice here. Upsampling to 16 kHz and using asynchronous recognition will likely give us the best results for long audio recordings.

upvoted 0 times