Research position (postdoc in speech synthesis) at IRCAM / CHANTER Project

Job offer: Non permanent researcher (W/M)
Expert in speech signal processing, and or speech synthesis (ANR project: CHANTER)

Availability:  start date: Jan 2014

Duration: 12 months (an extension of up to 6 months may be considered)

Introduction to IRCAM

IRCAM is a non-profit organization that is associated to the Centre  Pompidou (Centre national d’art et de culture Georges Pompidou). Its missions comprise research, production, and education related to contemporary music and its relation to science and technology. Within the R&D department specialized teams are conducting research and development in the areas of acoustics, sound signal processing, interaction, computer music and musicology. The present position is available in the analysis/synthesis team that conducts research on advanced algorithms for speech and music signal processing. IRCAM is located in the centre of Paris near the Centre Pompidou, at 1, Place  Igor Stravinsky 75004 Paris.

Introduction to the CHANTER project

The CHANTER project aims to realize a singing synthesis system that integrates recent advanced speech (singing) signal processing technologies into a TTC (Text to Chant) prototype system. The final singing synthesis system should not only allow offline synthesis but should as well support interactive control of the synthesis results. A sound database containing singing signals will be used as the basic singing unit reservoir of the system and state of the art speech processing technologies will be used for transforming the recorded singing units and for concatenating them into the final result. Strategies for the generation of all relevant singing voice parameter contours will be developed. The development of musically interesting strategies for the real time control of the synthesis system is one of the important research objectives.

Role of IRCAM in the CHANTER Project

The analsyis/synthesis team of IRCAM is in charge of the research and development the basic singing synthesis technology. This includes the appropriate representation of the singing sound database, the establishment of a concatenation and transformation procedure of the singing units under low latency constraints, and the generation of singing voice parameter contours.

Position description

The hired researcher will be in contribute to the project by means of developing different parts of the basic singing synthesis system. He/she will collaborate with other researchers working on different aspects of the analysis and synthesis technics. She/he will be required to participate in all activities related to the project (evaluation, meetings, specifications).

Required Experiences and Skills

-       PhD with excellent knowledge of and experience in speech signal analysis (f0, and other source parameters) and frequency domain speech signal processing     (analysis/synthesis, spectral domain filtering, shape invariant signal processing).
-       Excellent knowledge of and experience in signal models and time/frequency representations of sound signals.
-       Experience with speech synthesis systems (TTS).
-       Experience with machine learning techniques and statistical models.
-       Very proficient in Python (NumPY/SciPY), skills in C/C++ programming.
-       Good knowledge of Linux, and/or Mac OS X.
-       High productivity, capacity for methodical and autonomous work, creativity, good communication skills, rigor, and excellent programming style.

Salary

According to background and experience

Applications

Please send an application letter together with your resume and any suitable information addressing the above issues preferably by email to: roebel@ircam.fr

Deadline

November, 18th, 2013  (after this date applications will be considered until the position is filled)

See website

AIRSPLACE

AIRS staff are working towards providing the results of Project research, so that information and research findings can be shared amongst the researchers and interested individuals.  Please direct any questions or comments regarding the AIRS Web site to the AIRS Information Technology Coordinator. Contact information can be found on our Contact AIRS page.