True but problem with both is: do we have access to either

yes, implementations for emotion from voice are publicly available

i'm really not sure though what would be the point to plug that in a speech recognition system

If it recognizes what they sound like when they feel a certain emotion I imagined that when the words are implemented it can find how they would be pronounced under those circumstances considering looking at emojipedia many words can be labeled in multiple ways.

Seeing I’m only learning about things now I’m going to suggest many outlandish ideas

My Windows XP Tour narrator voice is going along well. I am transcribing the script to a text file.

wtf?

you're transcribing a TTS engine?

why?

you could just paste some text in and then it reads out what you put in...?

the Tour narrator voice is not Microsoft Sam

ok, link to the right audio?

worst animation movie of the 00s

lmao

It brings nostalgia to us all.

Ah, good ol nostalgia... Can't beat it!

so you watched it at the time?

several times...?

Many, many times my friend.

It's an essential part to installing Windows XP in my books.

couldn't you skip it?

You don't need to view it.

It's optional, but I view it everytime I install Windows XP on a computer or VM.

get in line buddy... There way worse stuff that considered animated...

I just finished filling the text file.

I will be putting it through the Tacotron now.

now I'm going to start creating the Ninjala lucy dataset if I am not lazy

I'm currently creating the dataset for the Windows XP Tour narrator, and I'm at Epoch 46

Yep