Audio Development Fun

I finally almost figured out how to make my computer sound like me! Recently I found myself playing with MaryTTS and finally finding all of the pieces for their voice import process. It’s a very tricky process requiring a LOT of hard to find dependencies. Once you get all the dependencies downloaded, compiled, and installed you have another tricky process configuring Mary to use them all. I’ve made two separate attempts at importing recordings of myself into Mary as a unit selection voice. With anyluck I should have an email which will allow me to get the final tool required to import as an HMM voice.

I’m learning so much about digital audio and now my new toy of choice is SOX. I’ve used it to batch trim the quiet parts off of all of my 100+ recordings. This is probably important to the voice importer as I contantly hear blips and blurbs of the quiet parts of my recordings in the synthesized output. I really wish I could babble more but its late and I need to get some rest for tomorrow.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s