System identification with adaptive lattice filters for speech data

  • Wenxia Shi Dept. of Electrical and Computer Engineering, University of Western Ontario, London, Ont. N6A 5B9, Canada
  • Vijay Parsa Dept. of Electrical and Computer Engineering, University of Western Ontario, London, Ont. N6A 5B9, Canada
  • Jagath Samarabandu Dept. of Electrical and Computer Engineering, University of Western Ontario, London, Ont. N6A 5B9, Canada
Keywords: Adaptive filtering, Computational complexity, Data reduction, Least squares approximations, Mathematical models, Speech communication, Systems analysis, Affine projection algorithms (APA), Least mean squares (LMS), Speech signals

Abstract

The applications of adaptive lattice filter structures in modeling the response of hearing aids to speech signals were determined. Lattice based adaptive filter implementation include two approaches - the stochastic-gradient approach or gradient adaptive lattice (GAL), and the least-squares approach or least square lattice (LSL). Speech signals processed through modern hearing aids were analyzed using GAL filter and LSL filter. The performance of the algorithms were compared with least mean square (LMS), recursive least square (RLS), and affine projection algorithm (APA) in terms of computational complexity and modeling.
Published
2005-12-01
How to Cite
1.
Shi W, Parsa V, Samarabandu J. System identification with adaptive lattice filters for speech data. Canadian Acoustics [Internet]. 2005Dec.1 [cited 2019Aug.19];33(4):52-3. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/1780
Section
Proceedings of the Acoustics Week in Canada