Not really a leap forward so much as a synthesis of stuff that already exists. Same technology we have heard in the last several years, with added music.
And significantly worse voice synthesis than I've heard elsewhere. Most of Apple's Macintalk 3 voices (which are over 15 years old now!) sounded better than this.
The voices are ATT's. VocaTalk supports any SAPI 5.1/5.3 compatible voice. It combines music, binaural waves, and fx like positional audio to improve the experience. Those features create a unique experience that makes it possible to listen hours and hours of tts.
Listen with stereo earphones or earbuds. You'll notice several interesting features like echoes, positional audio. VocaTalk also supports voice modulation feature. This is all for reducing the monotony of tts and making it more fun to listen for hours.
I've heard that adding breaths into the mix are not just for the speaker, but that the listener can take that moment to mentally index what the speaker has just said. I can't find the paper at the moment, but there's been some good research that simply adding breathing sounds and pauses at key points in the audio can make listening to long TTS passage more bearable.
VocaTalk adds periods of silence between paragraphs. That gives you a break to think about the ideas given in the last paragraph while enjoying the music. They use the same technique in documentaries.
Also, VocaTalk uses all the installed voices on your system, and randomly changes the speaker for each paragraph. That's also great factor for reducing monotony. It also has other optional audio processing features like moving the voice location, echoes and dynamic voice pitch modulation.
7 comments
[ 2.5 ms ] story [ 19.2 ms ] threadhttp://speechprosody2010.illinois.edu/papers/100096.pdf http://www.springerlink.com/index/P32774KN22650J42.pdf http://www.softsea.com/review/Pistonsoft-Text-to-Speech-Conv...
I've heard that adding breaths into the mix are not just for the speaker, but that the listener can take that moment to mentally index what the speaker has just said. I can't find the paper at the moment, but there's been some good research that simply adding breathing sounds and pauses at key points in the audio can make listening to long TTS passage more bearable.