OSST

The Oldenburg Speech and Voice Test (OSST for short) is a tool used in the screening of voice and speech disorders. It is intended to support speech and language training for hearing disorders or after provision with a hearing device.

In order to provide a service for the automatic analysis of speech and voice disorders for research as well as speech and language therapy care, algorithms of automatic speech recognition and analysis and machine learning were combined in the SVAT (Speech & Voice Analysis Technologies as a Service) project of the Hearing, Speech and Audio Technology HSA section of the Institute. The OSST project is technologically based on analysis functions of the SVAT service and extends them with specific modules. In the first phase of the project, the focus is on the technical development of the analyses as well as the task concepts for the analysis of voice function, speaking style and speech intelligibility. Afterwards, the focus will be on the technical evaluation of the analysis procedures and the implementation as an assessment tool.

Evaluation modules for voice function, prosody, pronunciation and speech intelligibility are intended to provide patients in adulthood, therapists and physicians with objective feedback for screenings before and after provision with a hearing aid as well as during speech and language therapy supply. 

Due to the efficient and automated feasibility of the OSST as an online tool or app, a large screening frequency or group of people can be reached with little effort. The tool can thus accompany patients throughout the entire rehabilitation and therapy process, identify speech therapy needs and objectively present the course of therapy and care results. For the development of the analysis tool, we cooperate with the HAWK Göttingen as well as the Jade University of Applied Sciences Oldenburg.

The goal is to establish OSST as an easy and objective procedure in the identification of speech and voice disorders.

"Our vision is for everyone to be able to communicate with their voice," says Laura Tuschen, head of the Assistive Speech and Language Analysis group. The researchers are working on digital solutions to achieve this. In the video, Laura Tuschen explains how they are doing this and what needs to be taken into account, giving the OSST project as an example.