Automatic detection of speech disorders with the use of Hidden Markov Model

Marek Wiśniewski, Wiesława Kuniszyk-Jóźkowiak, Elżbieta Smołka, Waldemar Suszyński

Abstract


The most frequently used methods of automatic detection and classification of speech disordersare based on experimental determination of specific distinctive features for a given kind ofdisorder, and working out a suitable algorithm that finds such a disorder in the acoustic signal. Forexample, for detection of prolonged phonemes, analysis of the duration of articulation is used, andon the contrary, phoneme repetition can be detected with the spectrum correlation methods.Additionally, in the case of prolonged phonemes, classification based on their kind is required(nasal or whispered phonemes, vowels, consonants, etc). Therefore, for every kind of a disorder, aseparate algorithm needs to be worked out.Another, more flexible approach is the application of the Hidden Markov Models (HMM). Forthe needs of the presented work, the HMM procedures were implemented and some basic tests ofspeech disorder detection were conducted.

Full Text:

PDF


DOI: http://dx.doi.org/10.17951/ai.2007.7.1.91-100
Date of publication: 2015-01-04 00:00:00
Date of submission: 2016-04-27 10:31:31


Statistics


Total abstract view - 415
Downloads (from 2020-06-17) - PDF - 0

Indicators



Refbacks

  • There are currently no refbacks.


Copyright (c) 2015 Annales UMCS Sectio AI Informatica

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.