[Elsnet-list] [Job]: PostDoc in Speaker Recognition at the Idiap research institute
marcel at idiap.ch
Mon May 21 15:45:23 CEST 2012
The Idiap Research Institute seeks qualified candidates for one postdoctoral research position in speaker recognition.
The research will be conducted in the context of a Swiss National Science Foundation project to support technology transfer.
Recently, Idiap proposed a novel approach for automatic speaker recognition . It has been shown to be more noise-robust and computationally efficient than existing approaches.
This makes it very suitable more particularly for applications intended for mobile devices, which are liable to be used in very noisy scenarios and possess comparatively limited computing power. However, the gain of processing power is also a significant advantage for desktop (or cloud-based) infrastructures, as it will allow allocating more computing power on subsequent tasks. The proposed approach is based on a set of binary-valued and parts-based features, contrary to standard cepstral features used in speaker recognition, which are holistic and real-valued. The chief advantages and improvements of this new approach are as follows:
1. The features are very simple and easy to compute. They involve only comparison and addition operations. This contrasts with the standard cepstral features, which involve many more computations.
2. The features are considerably more robust to different types of noise that are encountered by speech-related applications in a real scenario (for example, in mobile phone applications), compared to standard cepstral features.
The proposed approach is scientifically and technically established and offers all the guarantees to provide a low complexity and noise-robust SR technique. It has a huge potential for many applications and hence is perfect candidate for technology transfer.
 A. Roy, M-M. Doss, and S. Marcel: A fast parts-based approach to speaker verification using boosted slice classifiers. IEEE Transactions on Information Forensics and Security, 7 (1), pp 241-254, 2012.
The successful candidate will investigate further this approach, compare it to state-of-the-art approaches (JFA, PLDA) and propose extensions.
The research will rely on previous knowledge and software developed at Idiap and in the Biometric Person Recognition team ( http://www.idiap.ch/~marcel/professional/Research_Team.html ).
The postdoctoral researcher will report to Dr Sébastien Marcel ( http://www.idiap.ch/~marcel ), his/her responsibilities will include:
1. Research in the framework of project(s)
• Carry out research as stated in the assigned project(s), follow evolution of project
• Fulfill project-related assignments (evaluations, deliverables, ..) as requested
• Publish results (Favor journal papers and good conferences, Favor joint publications with other IDIAP staff and/or project partners)
• If required, participate in project meetings and boards
• When appropriate, assume leading role as IDIAP contact point or work package leader
2. Supervision of students: Help supervise PhD students and interns in collaboration with supervisors
3. Participate in various IDIAP activities and projects as requested by supervisor(s) or IDIAP management
The postdoctoral researcher should have a strong background in statistics or applied mathematics, optimization, linear algebra, signal processing, and machine learning.
Experience in one or several of the following areas is required: speech processing and statistical models.
The applicant should also have strong programming skills and be familiar with MATLAB, C/C++, various scripting languages such as Python and with the Linux environment.
Any applicant will undergo a series of tests including technical reading and writing in English and programming.
The starting date is immediate. The appointment is for 12 months with a possible extension up to 24 months. Salary is competitive.
Apply online by clicking here: http://www.idiap.ch/webapps/jobs/ors/applicant/position/index.php?PHP_APE_DR_9e581720b5ef40dc7af21c41bac4f4eb=%7B__TO%3D%27detail%27%3B__PK%3D%2710114%27%7D
Dr Sebastien MARCEL
Senior Research Scientist
Idiap research institute
Phone: +41 27 721 77 27
Fax: +41 27 721 77 12
Email: marcel at idiap.ch
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Elsnet-list