Exam AI-102 topic 1 question 18 discussion

Actual exam question from Microsoft's AI-102

Question #: 18
Topic #: 1

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.
Hot Area:

Show Suggested Answer

Suggested Answer:

Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-use-codec-compressed-audio-input-streams?tabs=debian&pivots=programming- language-csharp

by htolajide at Sept. 21, 2021, 4:31 p.m.

Comments

Submit Cancel

htolajide

Highly Voted 3 years, 2 months ago

The answer is correct

upvoted 28 times

Mll1975

3 years ago

I agree GetCompressedFormat https://docs.microsoft.com/en-us/dotnet/api/microsoft.cognitiveservices.speech.audio.audiostreamformat.getcompressedformat?view=azure-dotnet SpeechRecognizer https://docs.microsoft.com/en-us/dotnet/api/microsoft.cognitiveservices.speech.speechrecognizer.-ctor?view=azure-dotnet#Microsoft_CognitiveServices_Speech_SpeechRecognizer__ctor_Microsoft_CognitiveServices_Speech_SpeechConfig_Microsoft_CognitiveServices_Speech_Audio_AudioConfig_

upvoted 7 times

rdemontis

1 year, 1 month ago

correct answer. Thanks for the provided documentation

upvoted 2 times

...

sumanshu

Highly Voted 2 years, 11 months ago

We need to convert Streaming MP3 Data. So, option 1 is eliminated, as it's not a Audio Streaming function. rest 3 contains the keyword Stream. But, default audio stream format is WAV, and here we are passing MP3, So other then WAV, we need to pass compressed audio format, So correct answer is : AudioStreamFormat.GetCompressedFormat. and we need to recognize the speech to convert into the text - so, Speech Recognizer.

upvoted 12 times

...

CDL_Learner

Most Recent 7 months, 3 weeks ago

AudioStreamFormat.GetCompressedFormat(AudioStreamContainerFormat.MP3): This option is selected because the audio data is in MP3 format, which is a compressed audio format. The GetCompressedFormat method is used to get the format of the compressed audio data. AudioConfig.SetProperty: This is used to set a property of the AudioConfig object, not to get the format of the audio data. AudioStreamFormat.GetWaveFormatPCM: This is used to get the format of PCM audio data, not MP3. PullAudioInputStream: This is used to create a pull audio input stream, not to get the format of the audio data.

upvoted 1 times

...

Prodyna

1 year ago

appeared in november exam

upvoted 4 times

...

acsoma

1 year, 4 months ago

appeared in august exam

upvoted 4 times

...

zellck

1 year, 5 months ago

1. AudioStreamFormat.GetCompressedFormat. 2. SpeechRecognizer https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-use-codec-compressed-audio-input-streams https://learn.microsoft.com/en-us/dotnet/api/microsoft.cognitiveservices.speech.speechrecognizer?view=azure-dotnet Transcribes speech into text. Speech can arrive via microphone, audio file, or other audio input stream.

upvoted 5 times

...