Advanced Speech Processing (2015)

Description: In this course, research topics of current interest within advanced speech processing will be covered. The past decade have seen many advances in speech processing, in particular within automatic speech recognition, speech intelligibility and quality measures, speech modeling, noise reduction, beamforming, localization, feedback cancellation, and dereverberation. These have largely been spawned by new methodologies based on statistical signal processing, convex optimization, sparse approximations, machine learning, and distributed processing. This course will highlight some of these advances and go into detail about the fundamental principles and methods that they are based on as well as speech applications. It is organized as a series of lectures focusing on selected topics.

Prerequisites:
A basic knowledge of mathematics as obtained through undergraduate engineering studies. Knowledge of speech processing is an advantage but not a prerequisite.

Organizer: Prof. Mads Græsbøll Christensen, Dept. of Architecture, Design & Media Technology

Lecturers: Prof. Mads Græsbøll Christensen, Dept. of Architecture, Design & Media Technology, AAU, Prof. Søren Holdt Jensen, Dept. of Electronic Systems, AAU, Assoc. Prof. Zheng-Hua Tan, Dept. of Electronic Systems, AAU, Postdoc. Jesper Rindom Jensen, Dept. of Architecture, Design & Media Technology, AAU and Postdoc. Jesper Kjær Nielsen, Dept. of Electronic Systems, AAU

ECTS: 3

Time: 16-20 November, 2015

Place: Aalborg University

Zip code: 9220

City: Aalborg

Number of seats: 50

Deadline: 26 October, 2015