Exam AI-102 All Questions

View all questions & answers for the AI-102 exam

Exam AI-102 topic 3 question 59 discussion

Actual exam question from Microsoft's AI-102

Question #: 59
Topic #: 3

HOTSPOT
-

You are developing a streaming Speech to Text solution that will use the Speech SDK and MP3 encoding.

You need to develop a method to convert speech to text for streaming MP3 data.

How should you complete the code? To answer, select the appropriate options in the answer area.

NOTE: Each correct selection is worth one point.

Show Suggested Answer

Suggested Answer:

by SCyrus at Oct. 5, 2023, 11:49 a.m.

Comments

Submit Cancel

evangelist

Highly Voted 1 year, 4 months ago

first one has to configure the format as MP3, so "AudioStreamFormat" option is chosen. Second, since it is speech to text, the SpeechRecognition option is needed. The answer is CORRECT

upvoted 15 times

...

syupwsh

Most Recent 3 months, 2 weeks ago

1) AudioStreamFormat because it specifies the format of the audio stream, which in this case is MP3. The AudioStreamFormat class allows you to define the specific format of the audio data being streamed. 2) SpeechRecognizer because it is used for converting speech to text. The SpeechRecognizer class is designed to recognize speech from audio streams and convert it into text.

upvoted 1 times

...

krzkrzkra

10 months, 3 weeks ago

1. AudioStreamFormat 2. SpeechRecognizer

upvoted 4 times

...

JacobZ

11 months, 2 weeks ago

Same as question 18 in topic 1

upvoted 1 times

...

NagaoShingo

12 months ago

1. AudioStreamFormat 2. SpeechRecognizer

upvoted 2 times

...

omankoman

1 year ago

AudioStreamFormat SpeechRecognizer

upvoted 1 times

...

takaimomoGcup

1 year ago

audio_format = speechsdk.audio.AudioStreamFormat(compressed_stream_format=speechsdk.AudioStreamContainerFormat.MP3) recognizer = speechsdk.SpeechRecognizer(speech_config, audio_config)

upvoted 2 times

...

hkbnjos

1 year, 4 months ago

this question is same as Topic 1 Q18 but with different answer, which is correct?

upvoted 1 times

Mehe323

1 year, 2 months ago

The answers are the same. Both chosen are AudioStreamFormat and SpeechRecognizer, but in question 18 there is an additional method for AudioStreamFormat (GetCompressedFormat).

upvoted 3 times

...

rdemontis

1 year, 7 months ago

correct

upvoted 2 times

...

SCyrus

1 year, 8 months ago

Answer correct https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/python/console/speech_sample.py

upvoted 4 times

...