Speech and Language Technology for Disabled Persons
Hearing impaired people only have a minor frequency range available for reception of information in speech signals. These people do not benefit from normal hearing aids. To overcome this problem we have developed a technique for transforming speech signals from one frequency range to another maintaining as much information and "speech likeness" as possible. The technique is well suited for real time implementation (VLSI), primarily caused by numeric robustness of the algoritms. An example - a transformed token - is used to highlighting the benefits from using the technique.
Bibliographic reference. Hermansen, K. / Fink, F. K. / Hartmann, U. (1993): "Parametric transformation of speech signals", In SLTDP-93, 67-70.