Hello everyone.

We have decided to phase out the Mixed Reality Forums over the next few months in favor of other ways to connect with us.

The first way we want to connect with you is our mixed reality developer program, which you can sign up for at https://aka.ms/IWantMR.

The plan between now and the beginning of May is to clean up old, unanswered questions that are no longer relevant. The forums will remain open and usable.

On May 1st we will be locking the forums to new posts and replies. They will remain available for another three months for the purposes of searching them, and then they will be closed altogether on August 1st.

So, where does that leave our awesome community to ask questions? Well, there are a few places we want to engage with you. For technical questions, please use Stack Overflow, and tag your questions using either hololens or windows-mixed-reality. If you want to join in discussions, please do so in the HoloDevelopers Slack, which you can join by going to https://aka.ms/holodevelopers. And always feel free to hit us up on Twitter @MxdRealityDev.

Does speech recognition build a voice profile?

In this official MS site it is stated that speech recognition builds a profile of your voice and it gets better the more you use it. I have an app in Unity for the Hololens using the speech recognition engine.
Is it also building a voice profile?
Does it mean that recognition for users different to the main user will get worse since the profiling is not made for them?
Is this different for Unity and UWP apps?

Answers

  • Jimbohalo10Jimbohalo10 ✭✭✭
    edited May 2018

    Hi @jmmore
    The speech recognition comes from the article which uses the Windows Control panel. HoloLens does not have Control panel or the
    Windows Speech Recognition
    So Cortana runs most recognition which is of course Azure Cloud base and your login MSA, is where your speech profile is stored.
    So if your users are all on the same profile could be a problem
    Watch the video Microsoft HoloLens: Course 212 - Voice - Ch. 3 - Understanding and the Dictation Recognizer

  • @Jimbohalo10 said:
    The speech recognition comes from the article which uses the Windows Control panel. HoloLens does not have Control panel or the
    Windows Speech Recognition
    So Cortana runs most recognition which is of course Azure Cloud base and your login MSA, is where your speech profile is stored.

    Thanks for your answer, but I think this only applies to the dictation recognizer. I am using a dictation recognizer (which is Cortana-based and needs internet connection for working) but also the phrase recognizers (grammar and keyword). These recognizers do not need internet connection and I guess (but cannot find evidence) they are based on Windows Speech Recognition even if it is true that the Hololens control panel does not include this option. I am interested in knowing if phrase recognizers build a voice profile.

Sign In or Register to comment.