Speaker identification using diffusion maps
Yan Michalevsky, Ronen Talmon, Israel Cohen · 2011
In this paper we propose a data-driven approach for speaker identification without assuming any particular speaker model. The goal in speaker identification task is to determine which one of a group of known speakers best matches a given voice sample. Here we focus on text-independent speaker identification, i.e. no assumption is made regarding the spo-ken text. Our approach is based on a recently developed man-ifold learning technique, named diffusion maps. Diffusion maps enable embedding of the recording into a new space, which is likely to capture the speech intrinsic structure. The algorithm is tested and compared to common identification algorithms. Experimental results show that the proposed al-gorithm obtains improved results when few labeled samples are available. 1.