Re: New speech speed-up library available under GPL

  • From: Alex Midence <alex.midence@xxxxxxxxx>
  • To: programmingblind@xxxxxxxxxxxxx
  • Date: Wed, 10 Nov 2010 16:01:15 -0600

Such voices are aaailable from different sources in windows for use
with Jaws, window eyes and NVDA.  As you speek them up, they acquire a
quaver as if the reader were speaking while in a car or train going
over a bumpy road.  The invlection that has been coded into them is
close but not quite to that of human speech and it winds up being a
distraction to me personally since, on the one hand, they sound like
human speech but, on the other, the flaws in it make it apparent that
it is not to such an extent that it feels like finding an apple on a
table, taking a bite of it only to find your mouth full of confetti or
plaster.  ghghghaaak.


The robotic voices were best for me.

On 11/10/10, Bill Cox <waywardgeek@xxxxxxxxx> wrote:
> Hi, LE.  It is true the I can listen to sped up human speech faster
> than I can listen to Eloquence.  I believe I have decent comprehension
> possibly as high as 4X speed up, while I only use voxin, which is an
> old version of Eloquence, at 3.2X speed up.  However, my speed is not
> considered very fast.
> I suspect this means that for people without years of listening
> training, its easier to improve rapidly listening to human speech.  It
> remains to be seen if the "natural" voice TTS systems can be listened
> to at rates similar to Eloquence.  I'm hoping that they will do well.
> I do suspect that we could all listen faster to sped up human voices,
> but only if we get to train on a specific human voice.  We can't
> expect a specific person to read everything for us, so we'll have to
> make due with TTS systems to get really fast.
> Bill
> On Wed, Nov 10, 2010 at 11:21 AM, qubit <lauraeaves@xxxxxxxxx> wrote:
>> Hi -- I am wondering if that is a true statement -- that you can listen to
>> real speech faster than eloquence.  Like a lot of people addicted to
>> eloquence -- well it has been a great little synth and has the property
>> that
>> it can read at ridiculously fast rates without loss of comprehension, for
>> experienced speech users.  At slower speeds, it is true it is much easier
>> to
>> listen to more real-sounding voices.  But the robotic ones are the ones
>> you
>> can exploit -- or is that what you are trying to change?
>> I'm anxious to try your program. Perhaps I will download it when i have a
>> chance later this week.
>> Thanks -- sounds exciting!
>> --le
>> ----- Original Message -----
>> From: "Bill Cox" <waywardgeek@xxxxxxxxx>
>> To: <programmingblind@xxxxxxxxxxxxx>
>> Sent: Monday, November 08, 2010 6:40 PM
>> Subject: Re: New speech speed-up library available under GPL
>> Hi, Stefik.  There aren't any tutorials yet.  The project is too new.
>> I'm currently hacking it into speech-dispatcher to enable Linux users
>> to enjoy it.
>> I do believe it will be useful in a lot of places.  Mainly, I was
>> worried that excellent TTS systems like Eloquence are slowly going
>> away, leaving people with vision impairments with only slow natural
>> speech TTS systems.  Now I feel that problem is solved, as we can
>> speed up any natural TTS system and I think achieve very high
>> listening rates.  I've been testing my friends and family (they think
>> I'm weird, but that's nothing new).  My family can listen from 2.5X to
>> 3X faster than recorded without training, and my old school friend can
>> listen at 3.5X speed up.  I can listen at about 4X, but I've been
>> training to speed-listen for over a year.  All of us can listen to
>> real voices at faster rates than we can alisten to Eloquence.  This
>> leads me to be hopeful about the future of TTS.
>> Bill
>>> Any tutorials available for how you would use it with various existing
>>> speech architectures? This sounds like a useful project.
>>> Stefik
>>> On Mon, Nov 8, 2010 at 3:36 PM, Alex Midence <alex.midence@xxxxxxxxx>
>>> wrote:
>>>> On 11/4/10, Bill Cox <waywardgeek@xxxxxxxxx> wrote:
>>>>> I've release a new very simple library for speeding up or slowing down
>>>>> speech. It's primary strength is high quality at greater than 2X
>>>>> speed up. The code can be checked out with:
>>>>> $ git clone git://
>>>>> There are speech samples in the samples directory. The primary
>>>>> motivation for this library is to enable low speed speech synthesizers
>>>>> to play at high speed with high quality. My hope is that many will be
>>>>> as easy to comprehend as Eloquence, giving us a lot more options in
>>>>> high speed TTS.
>>>>> Bill
>>>>> __________
>>>>> View the list's information and change your settings at
>>>> __________
>>>> View the list's information and change your settings at
>>> __________
>>> View the list's information and change your settings at
>> __________
>> View the list's information and change your settings at
>> __________
>> View the list's information and change your settings at
> __________
> View the list's information and change your settings at
Alex M
View the list's information and change your settings at

Other related posts: