Tanya Kraljic is a designer and researcher for Nuance Communications. Leading multimodal UX, her work focuses on the strategy and design of speech experiences in mobile, wearable, in-home, and other emerging technologies. She has helped clients from startups to Fortune 100 companies navigate the space of natural language technology, conversational design, and predictive intelligence. Prior to joining Nuance, Tanya earned a PhD in cognitive psychology.
09:00 - 12:30Room 1
Learn about the design and development of multimodal voice interfaces. With the explosion of mobile and IoT technology over the past few years, voice has become a primary interaction method. Designers, developers, and product owners are finding themselves at the forefront of this cutting-edge, but often unfamiliar, field.
This workshop will provide an overview of the state of the art and science behind voice interfaces. Then, through examples, discussion, and hands-on activities, you’ll walk away with a solid understanding of how these interfaces are designed and developed, where the field is going, what your challenges and opportunities are, and how you can hit the ground running when you’re ready to get to work.
The workshop will be a combination of examples, discussion, and hands-on activities.
We’ll talk about the design of artificial intelligence and cognitive systems, chatbots, IoT and the vision of Zero UI. You’ll have the opportunity to design your own voice-enabled system, and we’ll discuss:
- What makes a good use case for voice and natural language?
- How do we make these interactions successful? Useful? Engaging?
- How do we make them intelligent? Do we want them to be?
- How do we learn from previous conversations in order to improve future ones?
We’ll also cover such fundamental topics as:
- Getting started: what challenges and opportunities will you face, how long will it take, what decisions will you have to make, and what might your tasks and deliverables be?
- Technology: What is the current state of the art in speech technology? How do speech recognition, natural language, dialog, and AI work together?
- Tools and APIs: How might the new self-service tools, cognitive and dialog APIs fit into your process?
No prior experience is assumed, everyone is welcome.
Opinions about and ideas for voice-enabled systems are a plus, but not required. You should definitely bring a pen and paper (or computer) for sketching out use cases and architecture.
16:50 - 17:25Auditorium I
“What if McLuhan is right? Suppose he is what he sounds like – the most important thinker since Newton, Darwin, Freud, Einstein and Pavlov?” – Tom Wolfe (1969)
Folks from within the community of UX practice have been calling for the death of the wireframe since the early ‘oughts. And now with the rise of Agile, the death-knell is ringing from without. Just so you know: they are coming for the rest of our deliverables.
How in today’s Lean world do we situate the role of depiction and documentation in our process? If in the past we were doing it wrong, how do we go forward doing it right?
This presentation introduces Marshall McLuhan’s four laws of media, as applied to UX design and software development. Attendees will learn how to analyze the media we use to depict, deliver and approve our ideas while avoiding subtle and pernicious traps that lurk in the interplay between medium and message.