Friday, April 29, 2011

PhD studentship: The learning speech interface

Jort Gemmeke, a reader and contributor to Nuit Blanche, sent me the following:

Hi Igor,
I wondered if you could add the following PhD position to your website for me? The research will focus on creating algorithms for self-learning & adaptive speech recognition, featuring a healthy dose of sparse representations, non-negative matrix factorization and related methods.
Sure Jort , Here is the announcement:

Junior researcher - The learning speech interface

Promoter: Hugo Van hamme

Description: A funded PhD position is vacant at the Centre for Processing of Speech and Images of K.U.Leuven, Belgium in the context of the ALADIN project (
The aim of ALADIN is to build a learning and adapting vocal  human-machine interface for controlling home appliances, games and personal assistants for users with a physical impairment. The interface should learn what the vocal characteristics of the user are, which words he/she uses and what he/she means with the spoken commands. Users can formulate commands in any way they like, using the words they like and only addressing the functionality they are interested in. Learning takes place by using the device, i.e., by mining the vocal commands and the change they provoke in the device. You will design adaptive learning strategies for acquiring and maintaining the user's vocabulary and their association to machine actions. To this end, you will refine modern machine learning techniques such as sparse coding, non-negative matrix factorization and spectral clustering. You will work in a multidisciplinary team of junior and senior researchers in machine learning, speech processing,
signal processing, user interface design and interest groups for physically impaired users.
Candidates should ideally have a Master or equivalent degree in engineering or computer science. Candidates with a math or physics degree and excellent programming skills may apply as well. Previous experience in speech recognition is not required but knowledge of or
experience in any the following areas form an asset:
* speech recognition and speech modelling
* programming experience in Matlab and Python
* strong mathematical and statistical background

Key words: machine learning, speech recognition, assistive technology
Latest application date: 2011-07-19
Financing: available
Type of Position: scholarship
Source of Funding: IWT
Duration of the Project : 4 years
Research group: Department of Electrical Engineering (ESAT)

No comments: