Rockbox.org home
release
dev builds
extras
themes manual
wiki
device status forums
mailing lists
IRC bugs
patches
dev guide



Rockbox mail archive

Subject: Re: voice file generation (Re: english.voice using AT&T
From: ruiner (ruiner1_at_charter.net)
Date: 2004-04-03


Wow, when I send from the correct e-mail address I'll bet this'll make it to
the list!

>Probably you mean "Resume" being spoken like curriculum vita?

That and it seems AT&T's TTS engine likes "mono" on it's own but "mono
right" and "left" turn into "Moe no"

>No real changes to the language file, it's not getting outdated so quickly.

>What parameters have you used to encode it? I had a look inside, half of
the
>file seems to be padding zeros. In general, you should use VBR to have more
>efficient coding. And because of a bug in changing from one clip to another
>it is currently better to disable the bit reservoir, Lame
parameter --nores.

>I have made a new program to generate the voice clips, see my tool
>collection:
>http://joerg.hohensohn.bei.t-online.de/archos/speech/voicefont/authoring_to
ols/
>The new one is "lang2wav", which generates the whole bunch of speech clips
>as .wav without a 3rd party program like TextAloud. Input is the .lang
file,
>it uses the default voice as configured in the Control Panel. After running
>it, you can batch-encode (maybe first batch-trim) the lot and run
"voicefont"
>to make the final language file. Result should be not larger than 1.5 MB,
else
>tune the encoder parameters. So the process is pretty simple now, and
>lang2wav is way faster than TextAloud.

Well it was actually about 15 minutes after I discovered your lang2wav
program that I put my first try together. I couldn't seem to get TextAloud
to work, though still thanks to it I have the AT&T voices. I encoded it with
your "make voicefont.cmd" in the same location, so unless it's depreciated
(and it does include vbr and nores) I can't explain why there were odd
results. Also in my more extensive testing (had to get to work the morning
i released!) I've noticed it sounds rather horrible!

>We're still waiting for a volunteer to do something similar under Linux
with
>e.g. the "Festival" TTS program, hint, wink. This could then be part of the
>automated build.

are the AT&T voices available under linux? after having them installed I'm
really quite spoiled!

Well I've updated the file on my webspace and at the very least it sounds
*much* better than my first attempt. (that url again is
http://webpages.charter.net/ruiner/english.voice )

_______________________________________________
http://cool.haxx.se/mailman/listinfo/rockbox



Page was last modified "Jan 10 2012" The Rockbox Crew
aaa