Q&A: Dirk Schnella-Walka, research scientist for multimodal system architecture at modality.ai, about the standardization of intelligent personal assistants.

Intelligent personal assistants, like Amazon's Alexa and Apple's Siri, are quickly taking control of people's lives, but there have been few standards to govern the technology. James Larson, co-chair of the SpeechTEK conference, talked to Dirk Schnella-Walka, research scientist for multimodal system architecture at modality.ai, about the standardization of intelligent personal assistants, which will be part of his SpeechTEK 2020 presentation.

What is the background of the group that you represent?

The main focus of the World Wide Web Consortium's Voice Interaction Community is to explore telephony-based applications beyond the VoiceXML standard languages, specifically intelligent personal assistants.

Who are the participants in your group?

Participants in this group come from various roles in companies interested in voice-based products. They include speech application developers and voice user interface designers. In general, they are all passionate about voice-based interaction.

What is your group trying to achieve?

Intelligent personal assistants have become a ubiquitous part of our everyday lives. Many personal assistants are dependent on hardware from certain manufacturers, making interoperability difficult. We are trying to explore the potential areas of standardization that will lower the barriers to use the services of intelligent personal assistants.

What is the current status of the work you have done?

The work is still in its early stages. We have identified the main building blocks of a general architecture and how its components should work together. We plan to define this in more detail.

While some vendor-dependent systems will remain, we are looking for ways to increase interoperability among personal assistants

How can readers of this article participate in your group?

The work is open and everybody is welcome to contribute. We maintain a GitHub repository that can be accessed by everybody to review the current state of our work. We invite people who are passionate to discuss these ideas with us either via our mailing list or by joining our bi-weekly calls.

To see presentations by Dirk Schnella-Walka and other speech technology experts, register to attend the SpeechTEK Conference in Washington April 27-29.