Exam AI-102 topic 3 question 13 discussion

, the best option is B. Upload a .zip file that contains a collection of audio files in the .wav format and a corresponding text transcript file. This method provides a balance of audio quality (with .wav files) and organization (having audio and transcripts together), which is essential for efficient and accurate training of speech recognition models.

A modified version of this was in the exam today.

https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-training-data#types-of-training-data Uploading a zip file s the standard method for uploading training data to Speech Studio. The .wav format is commonly used for high-quality audio, and pairing the audio files with a text transcript allows the Speech Studio to use the data for training models effectively. B is correct

B is answer.

For me and ChatGPT: B

wav zip

B is correct

Answer is correct

Answer is correct: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-voice-training-data#types-of-training-data

B is the Answer. Got this in Oct2023 exam

Same as Question 2. https://www.examtopics.com/discussions/microsoft/view/55251-exam-ai-102-topic-3-question-2-discussion

B is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-voice-training-data#types-of-training-data A voice training dataset includes audio recordings, and a text file with the associated transcriptions. Each audio file should contain a single utterance (a single sentence or a single turn for a dialog system), and be less than 15 seconds long. - Individual utterances + matching transcript A collection (.zip) of audio files (.wav) as individual utterances. Each audio file should be 15 seconds or less in length, paired with a formatted transcript (.txt).

B is correct answer. https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-speech-test-and-train