I’ve talked about the basics of designing a VUI and using Voiceflow to produce conversational prototypes. To make your life easier, I will keep this article short and efficient when introducing you to the concepts of VUI that any aspiring conversation designer should be familiar with.
If you have further questions and feedback, feel free to add a comment below.
As these have been covered plenty of times, I will only give a quick recap of their meaning. However, they are key in understanding conversation design.
Some of us remember Fireworks, the first tool I used to create a clickable prototype. However, while Adobe was focusing on its cash cows (Photoshop, Illustrator, InDesign, Flash) for years, user experience (UX) designers started to use Sketch around 2013–2014. At that time, I was creating prototypes in Axure RP and occasionally Illustrator for wireframes and basic illustrations. Given the power of these software packages, I was not impressed with Sketch initially. It looked simple with a limited set of features.
After using several applications that focus on producing Voice User Interfaces (VUIs), I’m more than certain that Voiceflow will become the industry-standard.
If you’re interested in designing and launching VUIs, I highly recommend you to pick up Voiceflow.
When you fire up Voiceflow, you will be asked to create a workspace and within that workspace, you can create projects.
Your workspace could represent an entity like your company, freelance business, or agency. You can change this at any time.
In order to understand how music and voice matching works, we need to understand how sound works. Most of us look at sound waves as simple 2D waves. However, sound is extremely complex, so I will be writing about the fundamentals of sound design to provide the reader with a better understanding of the subject.
In this article we will look at some of the key elements of sound and explain how they impact and produce sound.
The rate at which a soundwave completes a cycle, which is measured in Hertz (Hz). Human speech usually falls in the range of…
Every single year, we see a plethora of reports appear about next year’s UX and Design trends. Usually quite generic, and rarely containing novel content. The one trend and career path that has been a part of these lists for years now are AR and VR Design(er). If you’re planning on becoming a UX designer, you will have to step up your game either way as technologies keep improving at a rapid pace and users’ mental models keep changing at a rapid pace as well.
New AR and VR products keep hitting the market, with the latest ones removing the…
Before diving into the different types of voice and chat assistants, I’d advise having a quick read about the fundamentals of Voice User Interface (VUI) design.
More complex key terms will be explained in another article, such as Automatic Speech Recognition (ASR), natural language processing (NLP), Natural Language Understanding (NLU), Natural Language Generation (NLG), Text-to-Speech (TTS), Speech-to-Text (STT), among others.
However, for now, we’ll simply refer to the back-end system of a voice assistant as its engine.
These bots are frequently used to fulfil intents that fall within a small scope of requirements, for example “How can I retrieve my…
I’ve been a user of Adobe software for roughly 13 years, starting out with Photoshop, followed by Illustrator and InDesign. I produced my first wireframes in Illustrator, first prototype in Fireworks, and first website in Dreamweaver and, later on, Muse. Adobe is a company known for providing industry-standard software, especially its cash cow Photoshop that has been going strong for 30 years now.
They keep innovating, releasing new features and software, and are not afraid to kill or replace tools, such as Flash, which has been replaced by Animate. …
Multimodal design is the art and science of creating a user interface that includes multiple touchpoints using different modalities. The concept is to produce an interface that combines these different modalities that organically fit together, such as using voice as an input mechanism and a graphical user interface as the output for the user. Instead of relying on one modality, multimodal design doesn’t exclude any type of input or output.
Let’s start with the basics: input and output modalities. Think of an input modality as any way of interacting with a system. This could be through your mouse, keyboard, or…
Most bots that we interact with today, whether they’re chatbots or voice assistants, are scripted. In other words, they follow a certain tree structure, unlike AI-powered assistants.
AI assistants are evolving at a rapid pace. In one of my previous articles, which outlines the fundamentals of designing a VUI, we explain how the intent triggers an assistant to start a relevant interaction with the user. However, we should broaden the term “intent” since no verbal communication is required from the user to set an AI assistant in motion. …
More and more websites and apps are integrating chat functionalities. These are often connected to a service agent or a scripted bot to resolve simple issues. However, the traditional and confined chatbox is often disconnected from the application, service, or website. We use it to complain, to ask simple questions, and sometimes to work out more complex issues. Users usually resort to chat because information or features are unclear or missing.
This approach may work in many cases, but it’s worth thinking about improving the traditional conversational experience, making it more meaningful, perhaps even pleasurable.
Let’s start with a simple…
Global Design Lead at HSBC, Conversational Banking • Managing UX, UI, VUI design • University of Cambridge: Executive MBA ’20 - ‘22 • Hong Kong based