Context

Voice User Interfaces (VUIs) have rapidly become an integral part of our daily lives. Enabled by advances in natural language processing and artificial intelligence, VUIs allow users to interact with machines using spoken language, making technology more accessible and user-friendly.

From virtual assistants like Siri and Alexa to interactive phone systems and automotive infotainment, VUIs have found their way into diverse applications, promising a seamless bridge between humans and machines

While the potential of VUIs is immense, their effectiveness hinges on the ability to establish a coherent and natural form of communication between users and machines. In this context, communication breakdowns emerge as a critical challenge.

Problems

User's interaction issues with VUI'S

A- Speed and accuracy                                                            

  • Slow or fast response, missing words output.
  • failed to understand their queries correctly.

B- Interference in Discourse

  • Conversational assistant's responses disrupted the natural flow of conversation.
  • Misunderstandings or disjointed interactions.

C- Usability

  • Challenges in navigating and interacting with the voice user interface effectively.
  • Convoluted menu structures, unclear voice commands, difficulty in accessing specific features.

D- Natural Language Processing

  • Assistant struggled with understanding colloquial language, accents, or complex sentence structures.
  • Not handling a diverse range of user inputs.

Audience

People frequently using voice user interface systems and first timers using voice user interface.

Design Process

Why? 

Why people like interact with voice systems? 

Because its easier to do mundane task like setting up an alarm.

Why people prefer to do easy task with voice systems? 

They finds it quite unique to interact with voice as it's hand free.

Why do they find it unique?

As Voice systems offers a certain confidence in the interactions, that triggers people's innate communication system.

Why voice system triggers people communication system? 

They think it'll might reduce their screen time and eventually cognition load.

Why do they think voice systems will reduce screen time & cognition load? 

Because people feel voice systems will communicate with them in human alike interactions.

Hypothesis

The study explores intrinsic user's communication behavior with a voice user interfaces. Further recognizing machine perspective while inspecting machine learning models used in voice systems.

31.25%

Drop in user task completion while interacting with voice user interface

26.74%

Drop in user satisfaction while interacting with voice user interface

Prototype playground

Sam, an avid music listener, was traveling to his office when he asked the VUI to play his travel playlist. Imagine yourself as sam and here's your script when you converse with voice system.

  • Play Jason Mraz's 'I'm Yours' on Spotify.
  • Sure/yes
  • Sure/yes
  • I already told you. I want to play it on Spotify

Follow the dialogue script states and interact with voice and text systems, note down your frustrations or the things you liked and reach out to me to talk about voice systems and all things UX.

Voice prototype

Text Prototype

Research process