Idiap has a new opening for a postdoc position in automatic speaker recognition
The Idiap Research Institute seeks a qualified candidate for postdoctoral position in automatic speaker recognition.
The research and development will be take place in the context of SNSF funded project Unified Speech Processing Framework for Trustworthy Speaker Recognition (UniTS). Broadly, the research will focus on learning speaker-related features directly from the speech signal with minimal prior knowledge using deep learning methods, and employing them to build better speaker recognition and speaker diarization systems.
The successful candidate will be part of the Speech and Audio Processing group and the Biometric group at Idiap. She or he will work under the supervision of Dr. Mathew Magimai Doss and Dr. Sebastien Marcel and in collaboration with the PhD student funded through UniTS.
The ideal candidate should hold a PhD degree in computer science, electrical engineering or related fields. She or he should have a background in signal processing, applied mathematics, optimization and linear algebra. The applicant should also have strong programming skills and be familiar with Python/Perl, C/C++, shell scripting and with the Linux environment. The R&D; will rely on previous knowledge and open source software developed at Idiap, more specifically Bob toolkit and other open source machine learning tools such as, Torch, TensorFlow. A solid experience in speech processing or machine learning or both is an asset.
The position is offered for one year, with a possibility of extension based on the performance of the candidate and the funding availabilities. The start date is flexible (until June 2017) and the annual gross salary is CHF 80,000.
To apply for this position, click on the following link: postdoc position in automatic speaker recognition