An HMM system for recognizing articulation features for arabic phones

Hosam Hammady, Osama Badawy, Sherif Abdou, Mohsen Rashwan

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

Abstract

In this paper, we introduce a Hidden Markov Model (HMM) recognition system for the articulation features of Arabic phones. The low-level features are described by Mel-Frequency Cepstral Coefficients (MFCCs). The created HMMs directly model certain articulation features (fricative and plosive). Classification is done on these features regardless of the phone itself. The model has been created successfully and tested on reference speech data. The error rate is very low for many phones and acceptable for most of them. Accordingly, the system output can be used as a confidence measure applied to other existing speech recognizers. Finally, the recognizer is speaker-independent and context-independent.

Original languageEnglish
Title of host publication2008 International Conference on Computer Engineering and Systems, ICCES 2008
Pages125-130
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2008
Event2008 International Conference on Computer Engineering and Systems, ICCES 2008 - Cairo, Egypt
Duration: 25 Nov 200827 Nov 2008

Publication series

Name2008 International Conference on Computer Engineering and Systems, ICCES 2008

Other

Other2008 International Conference on Computer Engineering and Systems, ICCES 2008
CountryEgypt
CityCairo
Period25/11/0827/11/08

    Fingerprint

Keywords

  • Feature extraction
  • Hidden markov models
  • Speech recognition

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Hammady, H., Badawy, O., Abdou, S., & Rashwan, M. (2008). An HMM system for recognizing articulation features for arabic phones. In 2008 International Conference on Computer Engineering and Systems, ICCES 2008 (pp. 125-130). [4772980] (2008 International Conference on Computer Engineering and Systems, ICCES 2008). https://doi.org/10.1109/ICCES.2008.4772980