In this paper we present a study of automatic speech recognition systems using context-dependent phonemes and graphemes as sub-word units based on the conventional HMM/GMM system a...
In this paper, we present a microphone array beamforming approach to blind speech separation. Unlike previous beamforming approaches, our system does not require a-priori knowledge...
We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1]...
Carl Henrik Ek, Philip H. S. Torr, Neil D. Lawrenc...
This paper explores the issue of term-weighting in the genre of spontaneous, multi-party spoken dialogues, with the intent of using such term-weights in the creation of extractive ...
Abstract. This article presents an ego-centric approach for indexing and browsing meetings. The method considers two concepts: meetings’ data alignment with personal information ...