Speech processing (medicine)

In medicine, methods of automatic language processing are used for the objective assessment of speech and voice disorders ( dysphonia ). In contrast to conventional invasive methods , no invasive process is necessary for automatic speech processing ( speech recognition ). Therefore, these methods are also suitable for children and the elderly, as there is no risk associated with the examination.

There are essentially two approaches to automatic examination by a speech processing system: the examination of sounds held (often vowels, such as a long "A") and the examination of read speech.

Examination of held vowels

The investigation of held sounds has been known for a long time. The following are to be named as representatives:

Dysphonia Severity Index (DSI) to measure voice quality
Teager Energy Profile for Assessing Hypernasality in Vowels
Jitter and Shimmer for evaluating the roughness

The disadvantage of the methods is often mentioned that a single vowel cannot represent the language. The DSI tries to remedy this situation by calculating various phonation paradigms (maximum phonation duration, highest generated frequency, lowest tone intensity and jitter) to form a measure.

Investigation of read language

This approach is a new method that only became possible with the advancement of speech recognition technology . A known text such as B. The sun and wind presented, which he has to read into a PC microphone. The speech recognizer then determines the spoken word chain and can carry out various analyzes with which z. B. can determine the intelligibility.

Automatic intelligibility analysis using speech recognition

swell

↑ F.Wuyts, MD Bodt, G. Molenberghs, M. Remacle, L. Heylen, B. Millet, KV Lierde, J. Raes, and PV Heyning. “The Dysphonia Severity Index: An Objective Measure of Vocal Quality Based on a Multiparameter Approach”. Journal of Speech, Language, and Hearing Research, Vol. 43, pp. 796-809, 2000.
↑ D. Cairns, J. Hansen, and J. Riski. "A Noninvasive Technique for Detecting Hypernasal Speech using a nonlinear Operator". IEEE Transactions on Biomedical Engineering, Vol. 43, No. 1, pp. 35-45, 1996.
↑ A. Maier, E. Nöth, A. Batliner, E. Nkenke, and M. Schuster. "Fully Automatic Assessment of Speech of Children with Cleft Lip and Palate". Informatica, Vol. 30, No. 4, pp. 477-482, 2006.

[1] F.Wuyts, MD Bodt, G. Molenberghs, M. Remacle, L. Heylen, B. Millet, KV Lierde, J. Raes, and PV Heyning. “The Dysphonia Severity Index: An Objective Measure of Vocal Quality Based on a Multiparameter Approach”. Journal of Speech, Language, and Hearing Research, Vol. 43, pp. 796-809, 2000.

[2] D. Cairns, J. Hansen, and J. Riski. "A Noninvasive Technique for Detecting Hypernasal Speech using a nonlinear Operator". IEEE Transactions on Biomedical Engineering, Vol. 43, No. 1, pp. 35-45, 1996.

[3] A. Maier, E. Nöth, A. Batliner, E. Nkenke, and M. Schuster. "Fully Automatic Assessment of Speech of Children with Cleft Lip and Palate". Informatica, Vol. 30, No. 4, pp. 477-482, 2006.