-
I have a question if you can explain it please:
1. In the embedding_manifest.json you add two .wav paths. You model spkr.nemo is only trained on the an4 dataset only. So the paths in embedding_ma…
-
In prediction，I only find bleu and distinct，not emotion accuracy. How to calculate sentiment of the response. And I also have a little doubt. Emotions of context and golden response should be the sam…
-
### Start with the `why`:
One of the core value-adds of DepthAI is that it runs everything on-board. So when used with a host computer over USB, this offloads the host from having to do any of the…
-
**I have implemented Speaker Independent-Identification but every 10/6 times only voice is recognized.**
I have recorded speech in WAV format & Enrolled a user, & Identification audio i am getting …
-
#### Description
We're working on calling pyannote.metrics (specifically, to get identification error rate) from within R ([package tutorial](https://laac-lscp.github.io/ChildRecordsR/articles/Va…
-
Hi and big kudos to your asv-subtool with both academic and practical contributions!
I found the ResNET34 setting in the toolkit does not have a clear reference. While for other x-vector networks r…
-
It's not entirely clear to me how strict I should be when validating recordings. For example, sometimes someone speaks a word slightly differently than in the sentence: someone misreads it and says 'c…
-
I'm glad that the HTCDS 1.0 was just published this sunday.
While I, here as lexicographer, have no problem with the creators of HTCDS and the United Nations International Organization for Migratio…
-
-
It appears when mutter is used as a WM it has it's own configuration to manage monitors & resolutions. Apparently GNOME Settings knows how to configure it. Basically lightdm is running the display s…