Skip to main content
Speech CommunicationVolume 37, Issue 3-4, July 2002, Pages 283-302

Quadratic classifier with sliding training data set in robust recursive AR speech analysis(Article)

  Save all to author list
  • aInstitute of Applied Mathematics and Electronics, Kneza Miloša 37, 11000 Belgrade, Serbia
  • bUniversity of Belgrade, Faculty of Electrical Engineering, Bulevar Kralja Aleksandra 73, 11000 Belgrade, Serbia

Abstract

We propose a robust recursive procedure, based on a weighted recursive least squares (WRLS) algorithm with variable forgetting factor (VFF) and a quadratic classifier with sliding training data set, for identification of non-stationary autoregressive (AR) model of speech production system. Experimental evaluation is done using the results obtained by analyzing speech signal with voiced and mixed excitation frames. Experimental results have shown that the proposed robust recursive procedure achieves more accurate AR speech parameter estimates and provides improved tracking performance. © 2002 Elsevier Science B.V. All rights reserved.

Author keywords

AR speech analysisLP parametersQuadratic classifierRobust recursive estimationSliding training data set

Indexed keywords

Engineering controlled terms:AlgorithmsLeast squares approximationsMathematical modelsRegression analysisSpeech production aids
Engineering uncontrolled termsQuadratic classifersVariable forgetting factors (VFF)
Engineering main heading:Speech analysis

Funding details

Funding sponsor Funding number Acronym
04M02,1007

  • 1

    This paper was supported by Ministry of Sciences and Technology of Republic Serbia, projects no. 04M02 and no. 1007, through Institute of Mathematics SANU Belgrade and Faculty of Electrical Engineering, University of Belgrade, respectively. The authors wish to express their sincere thanks to the reviewer for valuable suggestions, which improved the final manuscript.

  • ISSN: 01676393
  • CODEN: SCOMD
  • Source Type: Journal
  • Original language: English
  • DOI: 10.1016/S0167-6393(01)00019-X
  • Document Type: Article
  • Publisher: Elsevier

  Marković, M.Ž.; Inst. of Applied Math. and Electron., Kneza Miloša 37, Serbia;
© Copyright 2019 Elsevier B.V., All rights reserved.

Cited by 2 documents

Kovačević, B. , Milosavljević, M.M. , Veinović, M.
Robust digital processing of speech signals
(2017) Robust Digital Processing of Speech Signals
Zhao, W. , Bhushan, A. , Santamaria, A.D.
Machine learning: A crucial tool for sensor design
(2008) Algorithms
View details of all 2 citations
Inform me when this document is cited in Scopus:
Set citation alert Set citation feed
{"topic":{"name":"Speech Communication; Voice Quality; Frequency Estimation","id":15083,"uri":"Topic/15083","prominencePercentile":63.88641,"prominencePercentileString":"63.886","overallScholarlyOutput":0},"dig":"e1e98e15d744c23efc383dd3cba25a6f2fba7264d27aa9d3165a1c170e722c1e"}

SciVal Topic Prominence

Topic:
Prominence percentile: