The No.1 Website for Pro Audio
 Search This Thread  Search This Forum  Search Reviews  Search Gear Database  Search Gear for sale  Search Gearslutz Go Advanced
synthesized computer voices Special Ef­fects Plugins
Old 5th September 2011
  #1
Lives for gear
 
musicl's Avatar
 

synthesized computer voices

This one's been bugging me..

I wanted to find out a little more about the programming of synthesized voices...say the voice in some sat nav's or web apps that you can type a sentence and the computer reads it out - surely they are not working of samples of real humans but computer programming to pronounce and 'read' what you type.

How does this work if it's not samples? Is it all just clever computer programming?

Remember that talk any program for the PC? This was only 300kb!! No samples of vowels here, surely!?

Old 6th September 2011
  #2
Gear Guru
 
Ethan Winer's Avatar
 

Lightbulb

Speech synthesizers are just that - they actually synthesize the sound of the vocal cord "buzz" plus the formant filtering of the vocal tract. See this:

Speech synthesis - Wikipedia, the free encyclopedia

--Ethan
Old 6th September 2011
  #3
Lives for gear
 
musicl's Avatar
 

That's a really interesting read, thanks very much. It looks like processing is so
mixed with real samples VS synth that it's hard to tell what system is what.

I wonder what system Steven Hawkins uses and if that has a partial sample library with DSP processing...

PS what's even more interesting is your dinner with gates and how his manners are
Old 7th September 2011
  #4
Gear Guru
 
Ethan Winer's Avatar
 

Lightbulb

As far as I know, all of the "typical" speech synthesizers create the sounds synthetically, with no samples.

--Ethan
Old 8th September 2011
  #5
GMK
Gear Nut
 
GMK's Avatar
 

It's an extensive subject, many people focus on speech while others focus on sung vocals. It's usually a pulse generated to emulate the cords themselves vibrating, then a filter bank with varying bandwidths, frequencies and boosts to emulate the formants of the chest cavity, the soft pallate the nose etc...basically every where you're body resonates the "buzz" from the vocal cords (which is really....everywhere but some places count more than otheres) The soft pallette and tongue formants are usually dynamic in that they change over time, as your tongue and the shape of your mouth do to form words. While noise generators are involved in recreating plosives and constanant sounds
Old 8th September 2011
  #6
Lives for gear
 
musicl's Avatar
 

You are both gentleman & scholars. Fascinating how human speech is reproduced.
Post Reply

Welcome to the Gearslutz Pro Audio Community!

Registration benefits include:
  • The ability to reply to and create new discussions
  • Access to members-only giveaways & competitions
  • Interact with VIP industry experts in our guest Q&As
  • Access to members-only sub forum discussions
  • Access to members-only Chat Room
  • Get INSTANT ACCESS to the world's best private pro audio Classifieds for only USD $20/year
  • Promote your eBay auctions and Reverb.com listings for free
  • Remove this message!
You need an account to post a reply. Create a username and password below and an account will be created and your post entered.


 
 
Slide to join now Processing…
Thread Tools
Search this Thread
Search this Thread:

Advanced Search
Forum Jump
Forum Jump