Loading...

A time warping speech recognition system based on particle swarm optimization

Rategh, S ; Sharif University of Technology | 2008

586 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/AMS.2008.156
  3. Publisher: 2008
  4. Abstract:
  5. In this paper, dynamic programming alignment is replaced by a particle swarm optimization (PSO) procedure in time warping problem. The basic PSO is a very slow process to be applied to speech recognition application. In order to achieve a higher performance, by inspiring of PSO optimization methodology, we introduced a PSO Inspired Time warping Algorithm (PTW) that significantly increase the computational performance of time warping in alignments of long length massive data sets. As a main enhancement, a pruning strategy with an add-in controlling threshold is defined in PTW that causes a considerable reduction in recognition time, while maintaining the system accuracy comparing to DTW. © 2008 IEEE
  6. Keywords:
  7. Alignment ; Alpha particle spectrometers ; Asset management ; BASIC (programming language) ; Crystal whiskers ; Mathematical programming ; Optimization ; Particle spectrometers ; Speech ; Speech analysis ; Speech recognition ; Systems engineering ; Weaving ; Computational performance ; International conferences ; Massive data ; Modelling and simulation ; Optimization methodology ; Pruning strategies ; Recognition time ; System accuracy ; Time warping ; Particle swarm optimization (PSO)
  8. Source: 2nd Asia International Conference on Modelling and Simulation, AMS 2008, Kuala Lumpur, 13 May 2008 through 15 May 2008 ; 2008 , Pages 585-590 ; 9780769531366 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/4530541