[mary-dev] Art/Technology residency in Spain, question/proposal

[Jaume Ferrete]

Thank you, Ingmar, for your answer.

In case we were to build a Spanish voice, as I am not a fluent coder, the
way I see I could contribute to the Spanish language components would be by
dedicating part of the grant's budget to it.

As I am only presenting an application, the most important aspect right now
is to determine the feasibility -thank you!- and to estimate the budget.
The budget should include all the technical aid needed to record and
develop a voice - I cannot do this myself- and possibly coding the Spanish
language components / improving the NLP code.

Would it be possible for you to help me estimate this, and/or possibly
suggest the people who could work with me in this project?

I hope I can bring something good to MARY TTS through this project.

Thank you very much.


Jaume

On Wed, Jan 21, 2015 at 6:33 PM, Ingmar Steiner <ingmar.steiner at dfki.de>
wrote:

> Dear Jaume,
>
> thank you very much for your message!
>
> I think that it's absolutely feasible to record and build a TTS voice in
> two months; in fact we do it in two weeks as a project seminar at Saarland
> University (next one coming up in February).
>
> Moreover, we are working on several projects with a growing group of
> people, and part of this involves a complete overhaul of the voicebuilding
> process; our development code is already working, and is expected to become
> more stable in the next few weeks. So it's a great time to become involved
> in MaryTTS, as the dev community is significantly larger and more active
> than it was in the not-too-distant past.
>
> One thing to keep in mind for your project, however, is that the Spanish
> language components are still rather basic (and not even merged into the
> upstream/master branch yet); so if you plan on building a Spanish voice,
> some further improvements to the NLP code work might be required ahead of
> time to improve the subsequent TTS enabled by your voice.
>
> Best wishes,
>
> -Ingmar
>
> On 21.01.15 14:14, Jaume Ferrete wrote:
>
>> Dear,
>>
>> This is an email related to developing a voice for MARY, as part of an
>> artistic residency and production grant. I kindly ask for the lists
>> oppinion on the feasibility of the project, and the possible involvement
>> or support of MARY TTS devs, as a collective or individually.
>>
>> I work as an artist, based in Barcelona, and I've been working for a few
>> years on the subject of the voice. I have been in residency, worked and
>> exhibited internationally, including at Museum of Contemporary Art of
>> Barcelona, District Berlin, Helsinki International Artists in Residency
>> Program, Urban Video Project (New York), Matadero (Madrid), Vessel
>> (Bari, Italy), Secession (Viena), and other venues. I am also part of
>> "Sons de Barcelona <http://barcelona.freesound.org/>" a sound pedagogy
>> project initiated by the Music Technology Group of Pompeu Fabra
>> University (MTG/UPF) and related to project Freesound
>> <http://freesound.org>.
>>
>> I am at the moment preparing a submission that involves MARYTTS for a
>> grant at LABoral <http://laboralcentrodearte.org/> ; an art and
>> technology related institution in Gijón, Spain. F
>>
>> I would like to develop a MARY TTS voice, exploring and expanding on the
>> process; documenting its different phases, paying attention to its
>> aesthetic and ideological implications, and putting them in context;
>> including its historical context regarding the reproduction of the human
>> voice.
>>
>> As I understand it, the process requires a professional team and proper
>> recording equipment. The grant is a two month residency, with a budget
>> of +- 8000€, and involves a final exhibition.
>>
>> As I do not have experience in the concrete process I am not sure if the
>> time is feasible, and if the budget would allow me to pay for the worrk
>> of the professionals that I need to develop the voice.
>>
>> It would be very helpful for me if you could give me your opinion on its
>> feasibility regarding the voice production process; and maybe if MARY's
>> devs would be interested in collaborating or supporting a project like
>> this in any manner.
>>
>> Thank you very much for taking the time to read this email, and your help.
>>
>> All the best,
>> Jaume
>>
>>
>> _______________________________________________
>> Mary-dev mailing list
>> Mary-dev at dfki.de
>> http://www.dfki.de/mailman/cgi-bin/listinfo/mary-dev
>>
>>
> --
> /**
>  * Dr. Ingmar Steiner
>  *
>  * Head of Independent Research Group
>  * Multimodal Speech Processing
>  * Cluster of Excellence MMCI
>  *
>  * Senior Researcher
>  * Language Technology Lab
>  * German Research Center for
>  * Artificial Intelligence (DFKI GmbH)
>  *
>  * Principal Investigator
>  * Collaborative Research Center SFB-1102
>  * Information Density and Linguistic Encoding
>  *
>  * Department of Computer Science
>  * Department of Computational Linguistics & Phonetics
>  * Saarland University
>  *
>  * Campus C7.4, Room 2.01
>  * D-66123 Saarbrücken
>  * @tel: +49-681-302-70028
>  * @fax: +49-681-302-4317
>  * @web: http://coli.uni-saarland.de/~steiner/
>  */
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.dfki.de/pipermail/mary-dev/attachments/20150121/d6b72f8a/attachment.htm