Methods: Artificial Neural Network, Support Vector Machines, i-vector, Non-negative Factor Analysis (NFA), Multitask Learning, Least-Squares-SVM, MFCC
E. Edwards, S. De Zilwa, N. Irwin, A. H. Poorjam, F. Avila, K. L. Lew, C. Sirota. "Systems and Methods for Machine Learning of Voice Attributes." U.S. Patent Application 16/889,326, December, 2020. [Link]
A. H. Poorjam, M. H. Bahari, and H. Van hamme, “A novel approach to speaker weight estimation using a fusion of the i-vector and NFA frameworks”, Journal of Electrical Systems and Signals, vol. 3, no. 1, pp. 47–55, 2017. [PDF]
A. H. Poorjam, S. Hesaraki, S. Safavi, H. Van hamme and M. H. Bahari, "Automatic Smoker Detection from Telephone Speech Signals", Proc. 19th International Conference on Speech and Computer (SPECOM), Lecture Notes in Computer Science, Hatfield, UK, 2017. [PDF] [Poster]
A. H. Poorjam, M. H. Bahari, and H. Van Hamme, “Speaker weight estimation from speech signals using a fusion of the i-vector and NFA frameworks”, Proc. International Symposium on Artificial Intelligence and Signal Processing (AISP), pp. 118–123, Mashhad, Iran, 2015. [PDF]
A. H. Poorjam, M. H. Bahari, V. Vasilakakis, and H. Van hamme, “Height estimation from speech signals using i-vectors and least-squares support vector regression”, Proc. 38th International Conference on Telecommunications and Signal Processing (TSP), pp. 1–5, Prague, Czech Republic, 2015. [PDF]
A. H. Poorjam, M. H. Bahari, and H. Van hamme, “Multitask speaker profiling for estimating age, height, weight and smoking habits from spontaneous telephone speech signals”, Proc. 4th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 7–12, 2014. [PDF]
A. H. Poorjam: Speaker Profiling for Forensic Applications, M.Sc. thesis, Department of Electrical Engineering, University of Leuven (KU Leuven), Belgium, 2014. [PDF]