Speech Confusion Index (Ø): A Recognition Rate Indicator for Dysarthric Speakers
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.
KeywordsRecognition Rate Speech Recognition Speech Signal Intelligibility Test Speech Recognition System
Unable to display preview. Download preview PDF.
- 3.Rosen, K., Yampolsky, S.: Automatic Speech Recognition and a Review of Its Functioning with Dysarthric Speech. Journal of Augmentative and Alternative Communication 16, 46–60 (2000)Google Scholar
- 4.Thubthong, N., Kayasith, P.: Incorporated Tone model speech recognition for Thai dysarthria. In: Proc. of 11th International Society for Augmentive and Alternate Communication, Natal, Brazil (2004)Google Scholar
- 5.Kent, R.D.: Hearing and believing: Some limits to auditory-perceptual assessment of speech and voice disorders. Journal of Speech and Hearing Disorders 7, 7–23 (1996)Google Scholar
- 6.Corman, T.H., Leiserson, C.E., Rivet, R.L.: Introduction to Algorithms. MIT Press, Cambridge (1990)Google Scholar
- 8.Kayasith, P., Thubthong, N., Theeramunkong, T.: Consistency Score: Dysarthric Speech Indicator for Modren Speech Technologies. In: Proc. of 12th International Society for Augmentive and Alternate Communication (ISAA 2006), Dusseldorf German (2006)Google Scholar
- 9.Shriberg, L., Kwiatkowski, J.: Phonological disorders III: A procedure for assessing severity of involvement. Journal of Speech and Hearing Disorders 47(3), 256–270 (1982)Google Scholar
- 10.Shriberg, L., Austin, D., Lewis, B.A., McSweeny, J.L., Wilson, D.L.: The percentage of consonants correct (PCC) metric. Extensions and reliability data. Journal of Speech, Language, and Hearing Research 40, 708–722 (1997)Google Scholar
- 11.Kayasith, P., Thubthong, N.: Computerized Intelligibility Test for Thai Speech Disorder. In: US - Thailand Symposium on Biomedical Engineering, Bangkok Thailand (2005)Google Scholar