Using customized Breaks with Audio Content Creation

Dr. Bernhard Ost 1 Reputation point
2021-04-08T06:53:25.587+00:00

Hello,

I'm using the Audio Content Editor and I want to insert customized breaks. I'm using the german neural speaker "Katja".

My Problem is that the custom breaks, that I have inserted, are always longer as I intend them to be.

I added a break of 50 ms between two sentences. For that I removed the dot after the first sentence, because a dot equals a break of approximatly 100 ms. That can be to long sometimes. In the SSML-code the break is 50 ms long. When I put the exported audio file of the two sentences in Audacity the break is approximatly 100 ms long. Am I doing something wrong?

Thank you for your help!

85661-editor.png

85604-ssml.png

85619-audacity.png

Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,657 questions
Azure AI services
Azure AI services
A group of Azure services, SDKs, and APIs designed to make apps more intelligent, engaging, and discoverable.
2,761 questions

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Yueying Liu 1 Reputation point
    2021-04-20T15:26:24.433+00:00

    There is an original break length between "Recap" and "Wissen".
    Creation <break time="50ms" /> is to add an additional 50ms break between the two words. So it's why you insert 50ms, the audio shows 100ms.

    But there may have another issue that different break time looks no significant difference. We are looking into it.

    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.