[mary-users] phoneme input

[Ingmar Steiner]

Dear Spencer,

On 12.03.2011 01:54, Spencer Lord wrote:
> Hi,
>
> Is it possible to provide input in the form of a sequence of phonemes,
> rather than text?
>
> If so
> 1.  can you provide some direction or samples code on this would be
> done?   is there an inputType?

In case you haven't found it yourself in the meantime, have a look at 
the PHONEMES input/output type. In case you're looking to override a 
faulty phonemization, please be aware that you could also specify the 
pronunciation of just a span of your input text:

<?xml version="1.0" encoding="UTF-8" ?>
<maryxml version="0.4"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns="http://mary.dfki.de/2002/MaryXML"
xml:lang="en-US">
Foo <t ph="' f n O r d">bar</t> baz!
</maryxml>

> 2.  what are the valid phonemes and what is the format of the input?

Depends on the language (i.e. locale). Have a look at e.g. these files:

openmary steiner$ find lib/modules -name allophones.\*.xml
lib/modules/de/lexicon/allophones.de.xml
lib/modules/en/gb/lexicon/allophones.en_GB.xml
lib/modules/en/us/lexicon/allophones.en_US.xml
lib/modules/ru/lexicon/allophones.ru.xml
lib/modules/te/lexicon/allophones.te.xml
lib/modules/tib/lexicon/allophones.tib.xml
lib/modules/tr/lexicon/allophones.tr.xml

Usually more or less follows SAMPA, with slight modifications.

Best wishes,

-Ingmar

>
> Thanks in advance,
> Spencer
>
>
>
> _______________________________________________
> Mary-users mailing list
> Mary-users at dfki.de
> http://www.dfki.de/mailman/cgi-bin/listinfo/mary-users

-- 
Ingmar Steiner
Postdoctoral Researcher

LORIA Speech Group, Nancy, France
National Institute for Research in
Computer Science and Control (INRIA)