| Autor: |
Veena Karjigi, Anjli Varghese, Sowmya M C |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
2019 4th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT). |
| Popis: |
Speech communication is the fundamental of an individual's participation in society. But this type of communicating medium is often disrupted by various types of physical disorder. Dysarthria is one such disorder that encapsulates various neuro-motor disorders that disrupt or impair the physical production of speech. Speech of dysarthric speaker is less intelligible when compared to normal speaker, which creates difficulty during communication. One way to improve the intelligibility of dysarthric speech is to modify the formants of dysarthric speech and resynthesize the speech using modified formants. In this work, we modify the formants of dysarthric vowels by using three different formant transformation techniques available. When tested on the same data with root mean square as evaluation parameter, it is found that use of probabilistic least square regression results in smaller RMSE compared to formant transformation using target features and joint density estimation. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
