10-06-2017, 06:51 AM
The main algorithms used for speaker recognition are k-Nearest neighbour, neural network and gaussian mixture models(GMM).
In this paper, we propose a new usable speech extraction method to improve the SID performance under the co-channel situation based on the pitch information obtained
from a robust multi-pitch tracking algorithm.
http://cse.ohio-state.edu/ shaoy/yang_ICASSP03.PDF
An abstract taken from Comparing speaker recognition techniques is available here:
http://hanckmannold/documents/SpeakerRec...Report.pdf
This paper presents a novel algorithm for reducing the computational complexity of identifying a speaker within a Gaussian mixture speaker model (GMM) framework.
check out here