Connectionists: 1-year research position on deep learning for distant-mic speech recognition

[Emmanuel Vincent]

Dear list,

We are offering a 1-year postdoc/R&D engineer position on distant-mic 
speech recognition in the context of a large-scale R&D project on voice 
control of home appliances involving 5 companies and 3 academic labs.

The successful candidate will conduct research on state-of-the-art 
acoustic model adaptation and contribute to transfer his/her ideas into 
a commercial ASR product. More specifically, we are interested in 
adapting DNN acoustic models to reveberation and noise conditions by 
exloring deep learning-based uncertainty propagation techniques in the 
line of [1,2].

Ideal start: March 2016 (possible until June)

Salary: 2600 to 3300 €/month gross depending on experience, plus free 
health insurance and additional benefits

Ideal profile:
- MSc or PhD in speech processing, machine learning, audio signal 
processing, or applied statistics
- proficient programming in C++, shell, Matlab/Python
- experience with Kaldi and deep learning software


To apply: send a CV, a motivation letter, a list of publications, and 
one or more recommendation letters to emmanuel.vincent at inria.fr and 
irina.illina at loria.fr.

Applications will be assessed on a continuous basis until Jan 15. Please 
apply as soon as possible before that date.

PS: if you happen to be at ASRU this week and you're interested by this 
position, please come and say hello.


References:

[1] A.H. Abdelaziz, S. Watanabe, J.R. Hershey, E. Vincent, D. Kolossa,
"Uncertainty propagation through deep neural networks", Interspeech 2015.

[2] Y. Tachioka, S. Watanabe, "Uncertainty training and decoding methods 
of deep neural networks based on stochastic representation of enhanced 
features", Interspeech 2015.

-- 
Emmanuel Vincent
PAROLE Project-Team
Inria Nancy - Grand Est
615 rue du Jardin Botanique, 54600 Villers-lès-Nancy, France
Phone: +33 3 8359 3083 - Fax: +33 3 8327 8319
Web: http://www.loria.fr/~evincent/