Idiap on LinkedIn Idiap youtube channel Idiap on Twitter Idiap on Facebook
Personal tools
You are here: Home Awards and Jobs News New opening for a PhD student position in the field of trustworthy automatic speaker recognition

New opening for a PhD student position in the field of trustworthy automatic speaker recognition

The Idiap Research Institute seeks qualified candidates for one PhD student position in the field of automatic speaker recognition. The research will be conducted in the framework of the SNSF funded project UniTS (Unified Speech Processing Framework for Trustworthy Speaker Recognition).

Broadly, the goal of an automatic speaker recognition system is to authenticate or to identify a person through speech signal. The overall goal of the PhD position is to develop novel features and models for trustworthy speaker recognition. Specifically, the doctoral student will investigate:

(1) learning of speaker-related features directly from the raw speech signal using up and coming deep learning techniques and their application to speaker recognition and speaker diarization.

(2) development of anti-spoofing techniques, i.e. countermeasures, to protect speaker recognition systems against spoofing attacks.

The proposed research is a collaboration between the Speech and Audio Processing group (Dr. Mathew Magimai Doss, main advisor) and the Biometrics group (Dr. Sebastien Marcel, co-advisor) at Idiap. Thus, will be part of both the groups but will be accommodated in the Biometrics Group once She or he joins. The research will also rely on previous knowledge and softwares developed at Idiap, more specifically Bob toolkit and Spear.

The ideal PhD candidate should hold a Master degree in computer science, electrical engineering or related fields. She or he should have a background in statistics or applied mathematics, optimization, linear algebra and signal processing. The applicant should also have strong programming skills and be familiar with C/C++, MATLAB (although this is not a plus), various scripting languages such as Python and with the Linux environment. Knowledge in speech processing and machine learning is an asset. Shortlisted candidate will undergo a series of tests including technical reading and writing in English and programming (in Python and/or C/C++). 

The successful PhD candidate will become a doctoral student at EPFL provided that the candidate is accepted by the Doctoral School at EPFL ( Appointment for the PhD position is for a maximum of 4 years, provided successful progress, and should lead to a dissertation. Annual gross salary ranges from 47,000 Swiss Francs (first year) to 50,000 Swiss Francs (last year). Starting date is immediate or to be negotiated in 2015.

To apply for the position, click on the following link: trustworthy automatic speaker recognition


Apr 22, 2015
Document Actions