speechd-discuss
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Comments on the Text to Speech "algorithm"


From: Bohdan R . Rau
Subject: Comments on the Text to Speech "algorithm"
Date: Sun, 14 Nov 2010 20:25:11 +0100

On Sun, 14 Nov 2010 18:26:24 +0000, Christopher Brannon
<chris at the-brannons.com> wrote:
> The most-frequently-used words could be cached in memory.
> Let's suppose a cache of 10000 words, for a memory footprint of 12
> megabytes.  That's acceptable on modern hardware, and it should be
> fairly responsive.

I have not so old phone (Nokia N73, I keep it because of Nokia Audiobook
application which does not work on newer versions of Symbian) - do you
think it's acceptable for my device?

BTW if you have only words, you probably loose all prosodic informations.
The phrase is not simply concatention of words. Phrase has its own
intonation (question, exclamation, sentence, comma, etc.). Of course - it's
possible to record all words (and all possible concatentions for last 4
syllables). But my terabyte disk is too small...

Please, don't reinvent the wheel!

ethanak
-- 
http://milena.polip.com/ - Pa pa, Ivonko!



reply via email to

[Prev in Thread] Current Thread [Next in Thread]