Building a database for automatic speech recognition in Parkinson’s disease

Disordered speech and voice may limit access to everyday voice activated devices (e.g., mobile phones, computers). These devices have automatic speech recognition (ASR) systems that have been trained on non-disordered speech. This makes it frustrating for individuals with speech disorders such as those accompanying Amyotropic lateral sclerosis (ALS), Down Syndrome and Parkinson’s disease (PD) to utilize these devices. Project Euphonia is an initiative by Google to make speech technology more accessible to individuals with non-standard speech. The first step in this process is to gather large numbers of speech samples from disordered speakers in order to train speech recognition systems. This paper reports initial work to collect speech data from individuals with PD to contribute to this project.

To receive a certificate for viewing this On-Demand webinar:

  1. View the webinar in its entirety (must be viewed in one sitting, cannot be paused or restarted).
  2. Email to request a certificate and include the name of the webinar you viewed.
  3. LSVT Global will verify your viewing of the webinar and email you a certificate.

NOTE: LSVT Global webinars are not state or ASHA-registered for CEUs so you will need to retain your certificate if you would like to self-report your activity.