How to Personalize a User’s Voice Experience

How can designers let users know all that is possible in a voice experience without overwhelming the user?

Personalization is a broad subject. It can range from using genomic DNA information for individualized wellness advice, to browser cookies for banner ads, but first and foremost, it should be seen as a way to provide a better user experience. Just adding a name to an email blast is not going to cut it.

In order to successfully create a tailored experience, we need to be aware of the different user journeys that our personas might traverse, and be smart about how we analyze data, so that we can automate the different directions that our experience might turn, flexing around the user needs.

This means, we’ll have to predefine a classification system for the different interaction metrics. These can range between some of the following: (but they’ll vary depending on the product)

  • Current User’s Actions
  • Previous User’s Actions
  • User Physical Context (location, time, day, weather, etc.)
  • User System Context (number of sessions, average session length, etc.)

Next, based on this information, we can do a few things:

  1. We can understand the user’s personal preferences and adapt the interface around this. For example, if a user always asks for the same series of things, we can “remember” it, and put it forward in the next interaction. This works much better in voice interfaces than visual ones, as change and adaptation is part of our natural way of communicating.
  2. We can also place the user in a different group tier, such as beginner, intermediate, advanced, where the interface gradually shifts based on how many times the user interacted with the app, and accelerated their journey was. We would pre-define the broader features and aspects of these different groups.
  3. The most common use of personalization has to do with recommendations based on plug-and-play machine learning algorithms, such as Amazon Personalize This is where you would keep track of specific user preferences, and use this to provide the user with other product recommendations, or paid for content as a way of monetization. Although I have yet to see this work for Voice.

In any case, personalization is not the sole answer to successful products. Here at RAIN, we are always thinking about the wider system where a product will exist, and with this mindset we create the most compelling experience possible.

For example, for the Starbucks voice assistant, we not only leveraged “your usual drink”, but also:

  • The location of the user and direction in relation to the closest shop
  • The ecosystem of other starbucks apps and tech
  • The primary Starbucks card balance and reward points
  • The different users who might have access to the app in the household

So if I ask for “my usual drink” the following will happen:

It’ll know it’s me, and that my usual drink is a triple grande macchiato in a venti cup, and that by the time the drink is ready I’ll be closest to the Times Square shop, which is when I’ll receive a notification on my apple watch, and I’ll pay for this entirely with my rewards points.

If we’ve done a good job at capturing data, we should be able to extract detailed quantitative metrics around the different flows and turns that people take when conversing with our products. Inserting this into a product analytics dashboard will greatly help to visualize user behavior flows, and identify drop-off points:

At RAIN we use our proprietary technology platform VOXA, to tag and track interactions, which we visualize through analytics platforms such as Dashbot and Google Analytics. In some cases we learned a great deal just from observing user flows that proved/disproved our hypotheses.

For qualitative feedback, we believe testing early is the way to go, and we strive to implement internal rounds during our design process as much as we can. We are trying to do more cross disciplinary, low-fidelity role playing testing internally during the earlier phases of design, but then when it comes to showcasing work to our clients, we’ve gone all the way to prototyping different flows with easy-build platforms such as Amazon skill blueprints. For later stages, we do technical testing through formal platforms by third party vendors.

Portions of this content originally appeared as part of SoundHound’s Finding Your Brand Voice: 6 Ways to Build a Better VUI Guide

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of"

nested selector system.

About RAINdrops 

Created and curated by our team of experts, RAINdrop articles cover the many ways voice technology is transforming your industry.

See All Articles

Get Voice on Voice 

Every Tuesday, our industry leading briefing covers the latest updates on voice and beyond. Join over 12,000 subscribers and sign up today.

Voice on Voice

Don't miss another briefing