5 Trends of Voice UI Design


At its core, the conception of interaction was invariably regarding communication. Human-Computer Interaction has never been regarding graphical user interfaces, that is why Voice User Interfaces (VUIs) square measure the longer term of interface design.

An interface is simply a medium individuals use to move with a system—whether it’s a user interface, VUI or one thing else. therefore Why is VUI therefore Important? 2 reasons:

Firstly, conversational interfaces square measure therefore fascinating as a result of speech may be a sort of communication everybody understands.

  • It’s a natural suggests that of interaction. individuals associate oral communication with people instead of with technology.
  • Users don’t have to be compelled to learn to interpret any symbology or new word (the language of GUI), they will use English (or the other native language) to work with a system. It doesn’t mean that users don’t ought to find out how to use a system however the educational curve be reduced considerably.

Secondly, user expectations square measure dynamic . in line with Statista, 39th of millennials use voice search. This audience is prepared to be the first adopters of VUI systems.

Top 5 VUI Trends

When it involves designing VUI, voice interaction represents the most important wife challenge for designers since the birth of the first iPhone. however the good news is that the foremost basic principles of UI design that we have a tendency to use once making merchandise with graphical user interface square measure still applicable to VUI design. Below you’ll realize a couple of trends that may form VUI design in next decades.

1. VUI That Builds Trust

Trust helps to create a bridge between an individual and a machine. If trust is absent, users are unlikely to act with a selected voice program.

The importance of the valid outcome (VUI ought to provide the person understanding that s/he can receive specifically what s/he requested). It’s potential to realize this goal by that specialize in the subsequent things:

  • Up the accuracy of speech recognition (more subtle natural language processing algorithms).
  • That specialize in understanding the user’s intent (a reason for interacting within the 1st place). once users act with a system, they need a selected downside they need to unravel, and also the goal of the designer is to grasp what this downside is.
  • Providing meaning error messages.
  • Crafting contextually driven flows. whereas it’s not possible to predict all commands that users would possibly raise the system, designers have to be compelled to a minimum of design a user flow that’s contextually driven. The system ought to anticipate users’ intent at every purpose of a spoken communication and supply users with info on what they’ll do next. for instance, finding a eating place close to the user. once users rummage around for a eating place, the system ought to match specifically what the user is searching for.

The importance of user management (one of the 10 Usability Heuristics for program design by Jakob Nielsen continues to be applicable to VUI design).

  • The system ought to think about the natural limitations of somebody’s brain (short-term memory limitations). the knowledge provided by the system ought to be overwhelming. once folks hear the system response, most users bear in mind only the last phrase. Thus, it’s higher to remain off from long phrases or providing a dozen completely different choices whereas the user will bear in mind simply a few of them at just the once.
  • The system ought to react to a user request with acceptable feedback. This feedback ought to provide users a full understanding of what the system is doing straight away. for instance, visual feedback lets the user understand that the system is prepared and listening; or in POD (Process of Doing). once a user sends missive of invitation to the system, the system shows a POD. POD isn’t a loading animation, it doesn’t simply state the actual fact that users got to wait whereas a system is doing one thing, it provides valuable info of what the system will. for instance, a POD for a command on family planning a file from Dropbox would possibly seem like as somebody rummage around for a right enter storage.

2. adaptive program

An adaptive program (also referred to as AUI) could be a program (UI) that adapts to the requirements of the user or context. VUI of the long run can adapt for users — the system can analyze all info it’s concerning users (including the knowledge concerning current status and health condition) and their current context to produce a lot of relevant responses to user requests.

For example, if a user contains a high pressure level at the present moment and decides to line a gathering in two hours, a digital assistant would possibly recommend avoiding that, or recommend lowering pressure level with exercise before the meeting starts.

3. VUI That Conveys temperament

Visual designers have tons of choices to introduce the temperament in graphical user interfaces – fonts, color, illustration, motion, simply to call a couple of. however what concerning VUI? Designers will convey temperament victimisation language itself — by fidgeting with words, voice, and tone. Speaking of voice, a voice is a component of the persona and it shapes its identity. Once we’ve associated a voice with one thing, it becomes a part of its identity. and that we expertise emotions after we act with such an interface, similar to we have a tendency to after we act with real folks. folks need human-understandable voices — not a voice that sounds human, however a voice that speaks coherently human!

Bad example: Siri voice by Susan bennett – the voice that sounds nearly human however folks still understand that it’s a machine. You can’t very have a dialogue with Siri. whereas you’ll raise Siri one thing like, “What is that the weather like today?” You can’t raise a lot of subtle queries like, “What ought to I wear today?” As a result, you don’t have deep feelings for Siri, you recognize it’s simply a golem.

Good example: Samantha voice from the film Her — the voice that sounds coherently human and folks are often infatuated with it.

4. From slim AI Towards General Intelligence

Human-computer interactions square measure shifting to spoken communication, however users expect a lot of. Most of AI systems on the market these days square measure still restricted to narrow AI — such systems use Machine Learning to unravel a clearly outlined (and, in most cases, manner too narrow) downside. slim AIs have zero data outside of their coaching information. It means once a user needs to unravel a rather completely different downside, or the matter itself evolves, the system won’t be able to solve it and it’ll respond with one thing like, “I don’t perceive.” so you, as a user, face a wall.

In comparison to slim AI, General Intelligence isn’t restricted to narrow domains. The thought of learning is at the inspiration of GI systems — the basic distinction between slim AI and General AI is that the overall Intelligence systems learn while not being expressly programmed (machines learn by themselves). GI system uses 2 sorts of learning — reinforcement learning (when a system uses all on the market info to unravel a selected user problem) and supervised learning (when a system desires user help to unravel a tangle for the primary time). Another distinction is that a General AI system will learn to utilize different AI for general and specific functions. As a result, completely different Machine Learning models are often trained dependently and work hand in glove. a sophisticated natural language {processing|NLP|human language technology|information science|informatics|information processing|IP} GI system is ready to find out from the primary try by combining and processing info from multiple completely different information sources.

5. Impact on Society

Widespread acceptance of VUI systems. up the standard of VUI AI-based systems can cause higher user engagement. The relationships between human and computer are interactive and cooperative — folks and computers can work along. this can impact society — simply imagine that in 10 years, you’ll walk into the house and simply speak and management all types of machines.

This future are with present AI: As users, we’ll trust AI even with the foremost necessary selections like “What college ought to i select for my children?” VUI can improve the standard of lifetime of older folks and folks with disabilities.


“The best interface is not any interface“ could be a notable quote of Golden Krishna, the author of the book the simplest Interface is not any Interface. He and lots of different designers believe that folks don’t need longer with screens, actually they need less. Thus, technology ought to stop celebrating screen-based solutions. And it’ll happen comparatively shortly — the interactions of the long run won’t be fabricated from buttons.

With the increase of pc process power, we’ll have a lot of systems that may be able to calculate up to a thousand steps in one second. A user and a machine can work along, enabling General Intelligence.

Leave a Reply

Your email address will not be published. Required fields are marked *