Improved silence-unvoiced-voiced (SUV) segmentation for dysarthric speech signals using linear prediction error variance

Tolulope Ijitona, Hong Yue, John Soraghan, Anja Lowit

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)

Abstract

A novel algorithm for the segmentation of dysarthric speech into silence, unvoiced and voiced (SUV) segments is presented. The proposed algorithm is based on the combination of short-time energy (STE), zero-crossing rate (ZCR) and linear prediction error variance (LPEV) or the segmentation problem. Extending the previous work in this field, the proposed method will address the difficulties in distinguishing between voiced and unvoiced segments in dysarthric speech. More precisely, the error variance of the linear prediction coefficients will be used to design a three-fold decision matrix that can accommodate the high variability in loudness experienced in dysarthric speech. In addition, a moving average threshold approach will be proposed in order to provide an 'as-fit' segmentation technique that is fully automated and that will be able to handle highly severe dysarthric speech with varying loudness and ZCRs. The ability of the proposed fully-automated algorithm will be validated using real speech samples from healthy speakers, and speakers with ataxic dysarthria. The results of the proposed approach are compared with known methods using STE and ZCR. It is observed that the proposed classification method does not only show an improvement in segmentation performance but also provides consistent results in low signal energy situations.

Original languageEnglish
Title of host publication2020 5th International Conference on Computer and Communication Systems (ICCCS)
Place of PublicationNew York
Pages685-690
Number of pages6
ISBN (Electronic)978-1-7281-6136-5
DOIs
Publication statusPublished - 18 May 2020
Event5th International Conference on Computer and Communication Systems - Shanghai, China
Duration: 15 May 202018 May 2020
http://www.icccs.org/icccs2020.html

Conference

Conference5th International Conference on Computer and Communication Systems
Abbreviated title ICCCS 2020
CountryChina
CityShanghai
Period15/05/2018/05/20
Internet address

Keywords

  • dysarthria
  • linear prediction coding
  • Linear Prediction Error Variance
  • speech disorder
  • SUV
  • voiced-unvoiced
  • zero crossing rate

Cite this