20 second Video limit for Pronunciation Assessment

Junbum Kwon 1 Reputation point
2021-07-18T12:26:25.97+00:00

Hello,

Today, we tried to analyze Video speech using the "Pronunciation Assessment". But, at one time, we were allowed to analyze only 20 seconds' videos.

How we can analyze the entire video (about 3 minutes)?

Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,675 questions

2 answers

Sort by: Most helpful
Most helpful Newest Oldest
  1. YutongTie-MSFT 50,856 Reputation points
    2021-08-04T23:56:48.01+00:00

    Hello,

    I have tried again on my side and it works for me well. As below screenshot, it's successfully with my 30sec audio. This is the sample code repo I am using, all of them are very convenient. https://github.com/Azure-Samples/Cognitive-Speech-TTS/tree/master/PronunciationAssessment/CSharp/Console

    120549-image.png

    Please let me any block for this and share the code sample you are using.

    Regards,
    Yutong

    0 comments
  2. Yinhe Wei 1 Reputation point Microsoft Employee
    2021-09-07T05:56:29.89+00:00

    Hi, @Junbum Kwon

    To handle long speech for pronunciation assessment, you can refer to below sample code:
    https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/python/console/speech_sample.py#L643

    It is based on continuous recognition and therefore it doesn't have limitation on length.

    Regards,
    Yinhe

    0 comments

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.