Afsaneh Asaei awarded the EPFL PhD degree for her work in sparse reconstruction applied to speech processing.
On September 4th 2013, Afsaneh Asaei, made the public defense of her PhD thesis entitled "Model-based Sparse Component Analysis for Multiparty Distant Speech Recognition". She received the EPFL diploma from her doctoral advisor (Hervé Bourlard).
My research takes place in the general context of improving the performance of the Distant Speech Recognition (DSR) systems, tackling the reverberation and recognition of overlap speech. Perceptual modeling indicates that sparse representation exists in the auditory cortex. The present project thus builds upon the hypothesis that incorporating this information in DSR front-end processing could improve the speech recognition performance in realistic conditions including overlap and reverberation. More specifically, the goal of my PhD thesis is to exploit blind (source) separation of the speech components in a sparse space, also referred to as sparse component analysis (SCA), for multi-party multi-channel speech recognition.
Congratulations to her.
For more details, please download the thesis here: Model-based Sparse Component Analysis for Multiparty Distant Speech Recognition.