Speech confusion index (Ø): a recognition rate indicator for dysarthric speakers

Authors:
Prakasith Kayasith;Thanaruk Theeramunkong;Nuttakorn Thubthong
Affiliations:
School of Information and Computer Technology, Sirindhorn International Institute of Technology (SIIT), Thammasat University, Pathumthani, Thailand;School of Information and Computer Technology, Sirindhorn International Institute of Technology (SIIT), Thammasat University, Pathumthani, Thailand;Acoustics and Speech Research Laboratory (ASRL), Department of Physics, Faculty of Science, Chulalongkorn University, Bangkok, Thailand
Venue:
FinTAL'06 Proceedings of the 5th international conference on Advances in Natural Language Processing
Year:
2006

Citing 1
Cited 2

Introduction to algorithms

Introduction to algorithms

Incorporated speech overlapped factor (Φ) into speech clarity index (Ψ): method to improve dysarthric speech severity evaluation

Proceedings of the 1st international convention on Rehabilitation engineering & assistive technology: in conjunction with 1st Tan Tock Seng Hospital Neurorehabilitation Meeting
Speech confusion index (Φ): A confusion-based speech quality indicator and recognition rate prediction for dysarthria

Computers & Mathematics with Applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents an automated method to help us assess speech quality of a dysarthric speaker, instead of traditional manual methods that are laborious and subjective. The assessment result can also be a good indicator for predicting the accuracy of speech recognition that the speaker can benefit from the current speech technology. The so-called speech confusion index (Ø) is proposed to measure the severity of speech disorder. Based on the dynamic time wrapping (DTW) technique with adaptive slope constraint and accumulate mismatch score, Ø is developed as a measure of difference between two speech signals. Compared to the manual methods, i.e. articulatory and intelligibility tests, the proposed indicator was shown to be more predictive on recognition rate obtained from HMM and ANN. The evaluation was done in terms of three measures, root-mean-square difference, correlation coefficient and rank-order inconsistency. The experimental results on the control set showed that Ø achieved better prediction than both articulatory and intelligibility tests with the average improvement of 9.56% and 7.86%, respectively.