Speech-analysis-based devices for diagnosis and education of speech and hearing impaired people

Two autonomous low cost devices which extract in real time some parameters of the voice, and perform a visual representation on a screen, are here described. Even though they can be useful in any voice related activity, they are in use at the moment in speech teaching to deaf people with good results. The first one, called SAS, displays a cross-section of the vocal tract and is based on the method proposed by Wakita (1); while the second one, named ISO-TON, makes a representation along the time of whether intensity, voiced/fricative condition of the voice, and fundamental tone.