==========================================================================

RESEARCH AND DEVELOPMENT POSITIONS IN SPEECH AND SIGNAL PROCESSING ==========================================================================

IRCAM is a leading non-profit organization dedicated to musical production, R&D and education in acoustics and music, located in the center of Paris (France), next to the Pompidou Center. It hosts composers, researchers and students from many countries cooperating in contemporary music production, scientific and applied research.
The main topics addressed in its R&D departement are acoustics, psychoacoustics, audio synthesis and processing, computer aided composition, user interfaces, real time systems.
Detailed activities of IRCAM and its groups are presented on our WWW server, http://www.ircam.fr/recherche.html

PROJECT PRESENTATION:
Synthesized images invaded many multimedia fields, animation, video games and films in particular. Parallel to this phenomenon, the voice remains today under-studied: most of the time, it is simply recorded by actors, synchronized often in a "manual" way with the movement of the characters and does not use any synthesis technique, except with rare exceptions.

The goal of the project is thus to allow the use of voice synthesis in multimedia in general and in other artistic applications like theatre. Among the principal research problems :
- Very specific voices must be produced,
- Synthesis must be of very high quality
- The creative and artistic destination necessitates at will modifications of the characteristics of the voices according to the particular or artistic effects desired.

The objectives that this project fixes require a certain number of conceptual and software means without which the production chain of synthetic voice could not function, and who are complementary: Methods:
- Transformation of voice identity
- Transformation of type and nature of voices
- Synthesis of expressive voice
- Text-to-Speech Synthesis
- Synthesis from corpus of actors and characters
- Interactive graphic user interfaces

Uses:
- Simple Doubling, or with effects and expressivity
- Text-to-Speech Synthesis, with effects and expressivity
- Post-processing

This project of the RIAM-ANVAR French network will be carried out in collaboration with France Telecom, IRISA, the Chinkel Studio and the BeTomorrow company.

DEVELOPMENTS TASKS: A position is available on November the first, 2006, in the Analysis/Synthesis team.
The position is planned for a duration of 18 months.

The candidate will perform the following tasks:
o Participation in the analysis of the needs and the establishment of the workplan
o Participation in the development of high quality speech synthesis
o Main contributor for improving automatic speech alignment/segmentation
o Participation in the development of expressive synthesis
o Participation in the definition of graphic interfaces
o Addition of new treatments and functionalities
o Participation in evaluations

REQUIRED EXPERIENCE AND COMPETENCE:
o Excellent experience in speech research and signal processing
o Experience in Matlab and C/C++ programming.
o Experience in speech recognition, alignment/segmentation (e.g. HTK) much appreciated
o Good knowledge of Unix environment.
o High productivity, methodical work, excellent programming style.

AVAILIBILITY :
- The position is available in the "Analysis/Synthesis" team in the R&D department on November the first 2006 for a duration of 18 months.

EEC WORKING PAPERS :
- In order to start immediately, the candidate should preferably have EEC citizenship or already own valid EEC working papers.

SALARY: - According to background and experience.

TO APPLY: - Please send your resume with qualifications and informations adressing the above issues, preferably by email to:
Xavier.Rodet@ircam.fr (Xavier Rodet, Analyse/Synthese team manager).
or by fax at: (33 1) 44 78 15 40, care of Xavier.Rodet
or by surface mail to: Xavier Rodet, IRCAM, 1 Place Stravinsky, 75004 Paris.