0

Conversational UI is common in IoT and other connected devices these days, not to mention smartphones and also computers. The main players in the market would probably be Siri from Apple, Alexa from Amazon, Google Assistant and Cortana from Microsoft.

It is typically rare for someone to own products from all of these vendors, but I wonder if there are some common conversational design patterns that are shared by these types of devices in the way they interact with the user, or if they are designed to behave differently to suit the particular target market or group, and where these differences might be.

The specific areas that I am thinking about from a user experience point of view are:

  • Choice of default voice (and variety available for customization)
  • Language used to trigger specific actions
  • Type of language used by voice assistant to respond
  • Type of audio cues and indicators for specific actions/status
2

Once I was at a VUI (Voice User Interface) conference, points I remembered:

  • voice customization - the voice of a 32 year-old woman or 18 year-old man?
  • NLP algorithms have a problem with understanding sarcasm / irony and indirect sentences
  • Reading emotions based on sound waves from your voice and adapting to this message is also a problem

Here You have more knowledge in this sphere:

https://medium.muz.li/voice-user-interfaces-vui-the-ultimate-designers-guide-8756cb2578a1 https://developer.amazon.com/docs/alexa-design/get-started.html

In this case, it is not based largely on the visible image, but on the decision tree / decision forest or other processes. In order to delve deeper into the topic, I recommend this publication on design patterns:

https://pdfs.semanticscholar.org/f4f8/619e2466d3c295052402896b7840c1099d90.pdf

|improve this answer|||||

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.