About the Speech Biomarkers Study

Many clinical disorders have symptoms that appear in spoken interaction, and for more than a century, doctors have evaluated patients' speech as part of their diagnosis.

The development of modern speech and language technology makes it possible to create automated methods for diagnostic screening or monitoring. Such tests require just a few minutes on the internet, rather than a visit to the clinic. But in order to create methods that are reliable across differences in age, gender, education, and other characteristics, we need results from a large and diverse group of normal people.

And it's especially important to create methods that can track an individual's changes across time. These methods can be used for early diagnosis, and also to evaluate possible interventions, like lifestyle changes or drug trials. To make such tracking possible, we need a large sample of people's responses to repeated encounters over weeks or months.

Your participation in this study will help us develop tests of this kind.

The data you contribute will be collected in a corpus that will be shared with individuals and organizations engaged in linguistic research, education, and technology development. Individuals and organizations that receive this material will first agree to use these resources only for these purposes.

Any personal identifying data we collect (for example, email address) is only visible to study personnel, is stored on our secure server and will not be distributed to individuals or organizations receiving the data. You will never be identified by email address or other personal identifier in any data sets, publications or presentations that may result from this research. You can leave the study or ask us to remove your data from our research database at any time.

If you have questions or comments, or if you want your data removed, please send us an email at speechbiomarkers@gmail.com.