Do you have any feedback and/or issues in regards to the Voice SDK? Use this place to discuss, as we'll have members of the team reviewing this thread!
Read the blog on Presence Platform (of which the Voice SDK is a part of) here: https://developer.oculus.com/blog/introducing-presence-platform-unleashing-mixed-reality-and-natural...
I've been playing around with the Voice SDK. I'd like to set up some simple words like "Ready" or "Let's go".
I've set up everything on Unity following the tutorial and the build-in words are working fine. So I've created some custom words on Wit.ai and imported them on my project. I've created Utterance like "Ready" and "Let's go" and set them under the same Intent "Start" (I selected the "English" language).
It's seems to work, but partially. Everytime I say "Ready" or "Let's go", I'm getting this :
> start matched, but confidence (0,00) was below threshold (0,60)
If I'm saying something else I don't get this line, so it seems to be detecting something.
The confidence never seems to go beyond 0. Am I missing something ?
Here's my settings for the Intent "Start", created directly from the "Understanding viewer" window
Also, I can confirm that that Wit can properly hear me saying "Ready" or "Let's go" as I'm doing a Debug.log on Transcriptions Events.
Well, as a "quick and dirty" fix I could just use the Transcriptions.Events and do a manual switch case on the results, but I'd like to understand why the proper way is not working.
Voice SDK does not seem to work with Unity 2021.2.2f1. Stack trace below:
Object reference not set to an instance of an object
Request Stack Trace:
at System.Environment.get_StackTrace () [0x00000] in <c183552e59b24622ab6b4273bc2ea328>:0
at Facebook.WitAi.WitRequest.Request () [0x00038] in C:\RalphVR\Easely\Easely\Assets\Oculus\Voice\Lib\Wit.ai\Scripts\Runtime\WitRequest.cs:212
at Facebook.WitAi.Wit.ActivateImmediately (Facebook.WitAi.Configuration.WitRequestOptions requestOptions) [0x000dd] in C:\RalphVR\Easely\Easely\Assets\Oculus\Voice\Lib\Wit.ai\Scripts\Runtime\Wit.cs:374
at Facebook.WitAi.Wit.OnSampleReady (System.Int32 sampleCount, System.Single sample, System.Single levelMax) [0x00260] in C:\RalphVR\Easely\Easely\Assets\Oculus\Voice\Lib\Wit.ai\Scripts\Runtime\Wit.cs:225
at Facebook.WitAi.Lib.Mic+<ReadRawAudio>d__55.MoveNext () [0x001cd] in C:\RalphVR\Easely\Easely\Assets\Oculus\Voice\Lib\Wit.ai\Scripts\Runtime\Lib\Mic.cs:301
at UnityEngine.SetupCoroutine.InvokeMoveNext (System.Collections.IEnumerator enumerator, System.IntPtr returnValueAddress) [0x00000] in <809a92a718b54e21a55192c70e75634b>:0
Response Stack Trace:
at Facebook.WitAi.WitRequest.HandleResponse (System.IAsyncResult ar) [0x000cd] in C:\RalphVR\Easely\Easely\Assets\Oculus\Voice\Lib\Wit.ai\Scripts\Runtime\WitRequest.cs:335
Facebook.WitAi.WitRequest:HandleResponse (System.IAsyncResult) (at Assets/Oculus/Voice/Lib/Wit.ai/Scripts/Runtime/WitRequest.cs:363)
Same project in 2019 worked fine with voice sdk. Is there a recommended version to use?
EDIT: Rolled back to 2020.3.22f1 and the sdk works.
So the problem is the NLU is coming back with a confidence < .6. This means it isn't confident that the intent it matched is the correct one. You can crank that confidence slider down lower, but what you really need to do is to go into the Wit.ai website and train a few more utterances for those intents.
^ confidence must be > this value (0.6) before the returned intent is considered an actual match.
Thanks for coming back to me !
So I did another test :
I created the intent "Repeat sequence" and added the following utterances :
> Do it again
> Start again
> Play it again
If I'm using the Curl commands with the utterance "Start again", I'm getting a confidence of 0.996.
On Unity, if I say "Start again" (which the app understand as I'm doing a Debug.log on the Transcription.events), it still says : "Repeat_sequence matched, but confidence (0,00) was below threshold (0,60)"
I'm not sure what I'm doing wrong at this point ?