Technical Reports (CIS)

Statistical Signal Processing with Nonnegativity Constraints

Lawrence K. Saul, University of Pennsylvania
Fei Sha, University of Pennsylvania
Daniel D. Lee, University of Pennsylvania

Document Type Conference Paper

Proceedings of the Eighth European Conference on Speech Communication and Technology, Eurospeech 2003 (Interspeech 2003), volume 2, pages 1001-1004. Held 1-4 September 2003, Geneva, Switzerland.


Nonnegativity constraints arise frequently in statistical learning and pattern recognition. Multiplicative updates provide natural solutions to optimizations involving these constraints. One well known set of multiplicative updates is given by the Expectation-Maximization algorithm for hidden Markov models, as used in automatic speech recognition. Recently, we have derived similar algorithms for nonnegative deconvolution and nonnegative quadratic programming. These algorithms have applications to low-level problems in voice processing, such as fundamental frequency estimation, as well as high-level problems, such as the training of large margin classifiers. In this paper, we describe these algorithms and the ideas that connect them.


Date Posted: 15 October 2004