[Elsnet-list] Job: Speech signal processing for expressive synthesis

Marc Schröder schroed at dfki.de
Tue Mar 7 11:46:48 CET 2006


The German Research Center for Artificial Intelligence (DFKI GmbH) is 
seeking for its Language Technology Lab a
                            RESEARCHER
in the area of speech signal processing, for a research position 
(Post-Doc, possibly junior) in the DFG project PAVOQUE ("Parametrisation 
of prosody and voice quality for concatenative speech synthesis in view 
of emotion expression").

The aim of PAVOQUE is to overcome the lack of expressivity of current 
unit selection synthesizers by combining the naturalness of corpus-based 
synthesis with the parametrisability of earlier technologies such as 
diphone and formant synthesis. PAVOQUE will carry out basic research on 
methods for the required parametrisation of the key parameters for vocal 
expression of emotion: prosody and voice quality. Two strategies will be 
pursued: parameter-based selection of units from the corpus, and 
post-processing of the synthetic speech signal with signal manipulation 
methods. This aims to provide a high degree of expressivity while 
maintaining good quality of the speech signal.

The responsibilities for the research position include, among others, 
the following:
* Proposal, implementation and assessment of signal analysis algorithms 
for labelling a speech synthesis corpus, particularly with prosodic and 
voice quality features;
* Proposal, implementation and assessment of signal modification 
algorithms for post-processing prosody and voice quality of selected 
units during synthesis;
* Contribution to the realisation of novel unit selection algorithms 
using the annotated features in selection and combining them with signal 
post-processing.

An ideal candidate will have a strong background in speech signal 
processing, some experience with speech synthesis, and clearly 
demonstrable experience with practical development of analysis and 
modification algorithms for speech prosody and voice quality. The 
candidate should be an experienced Java and/or C/C++ programmer. A 
broader interest in issues related to speech synthesis and 
expressive/emotional speech would be highly welcome. Highly valued 
personal qualities include team spirit, creativity, self-motivation, and 
the ability to communicate ideas clearly, combined with a determination 
to meet project goals

Ideally the applicant would have a completed PhD degree.

The earliest starting date of the position is May 2006. The initial 
duration of the contract will be two years, with a possibility for 
prolongation.

DFKI GmbH is located on the campus of Saarland University in 
Saarbrücken, Germany. The university's research groups and curricula in 
the fields of Computational Linguistics and Computer Science are 
internationally renowned. The LT-Lab offers excellent working conditions 
in a well-established research group. The position provides 
opportunities to collaborate in a variety of international projects. The 
competitive salary is calculated according to qualifications based on 
DFKI GmbH scales.

For more information on the PAVOQUE project, see 
http://mary.dfki.de/pavoque.

Please send your electronic application (preferably in PDF format) to 
lt-jobs at dfki.de, referring to job opening No. 200602, not later than 
March 31, 2006. A meaningful application should include a cover letter, 
a CV, a brief summary of research interests, a statement of interest in 
the position offered, and contact information for three references.

For questions concerning this job opening, please contact Dr. Marc 
Schröder schroed at dfki.de / http://www.dfki.de/~schroed.



-- 
Dr. Marc Schröder, Senior Researcher
DFKI GmbH, Stuhlsatzenhausweg 3, D-66123 Saarbrücken, Germany
http://www.dfki.de/~schroed
Here. Now. Real, first-person experience. Am I there to witness it?


More information about the Elsnet-list mailing list