Software Development Insights | Daffodil Software

How Voice User Interface can Add Value to your Application

Written by Twinkle Sharma | Feb 20, 2018 11:10:34 AM

The anatomy of web and mobile interface has undergone a major shift from Text User Interface, Graphical User Interface, Touch User Interface to Conversational User Interfaces (CUIs). This progress in UI models indicate the goal of creating user interfaces that closely reflect human communications. Since voice has been the core of human interactions, it is also becoming the new way we interact with gadgets and mobile devices.

The first era of VUIs were the interactive voice response (IVR) systems, which were capable of understanding human speech inputs over the telephone to automate and execute different tasks. IVR systems became capable of recognizing long continuous data strings such as Order tracking numbers, Account Number, Phone Number etc. but they failed when it came to parsing complex sentences with multiple chunks of information. In the second era of VUIs, mobile apps like Siri, Google Now, Hound, and Cortana, which combine audio and visual information are becoming mainstream. And not to forget VUI only devices, such as the Amazon Echo and Google Home, which have taken voice interactions to the next level.

“Tell me restaurants within two miles of my location, which are open right now". This isn’t a conversation between two people anymore. Today, you can not only search for services but can also place order, make transactions or do booking by just making a voice request to devices such as Amazon Echo and Google Home.

With this, imagine how many customers you can add on your platform by just being able to develop a product, wherein you don’t need to instruct the customers on how to use it. All that they need is to simply conversate with the product and get the aid for task accomplishment.

Some of the Popular VUI Platforms

Amazon Alexa:

  • Amazon Alexa is a cloud-based, voice controlled, intelligent personal assistant service that’s a part of millions of Amazon devices. Alexa enables developers to  build natural voice experiences that can offers users an intuitive way to interact with technology they use everyday.

    Applications: Amazon Echo is a brand of smart speakers developed by Amazon and powered by Amazon Alexa. Using Amazon Echo, you can create what are called “Skills”, which allow you to build custom interactions when speaking to the device. Alexa Skills Kit (ASK) helps you to add skills to Alexa, which is a collection of self-service APIs, tools, documentation, and code samples
  • Google Assistant is a virtual personal assistant by Google, primarily available on mobile and smart home devices. Unlike Google Now, the Google Assistant offers the advantage of engaging users in two-way conversations.

    Application: Google Home is a voice-activated speaker powered by Google Assistant. Google provides its own platform to build custom interactions called "Actions".

  • Apple Siri is an intelligent personal assistant, inbuilt in all Apple Inc.’s iOS, watchOS, macOS, and tvOS operating systems. Siri uses voice queries and a natural language user interface to understand and answer questions, make recommendations on the basis of prior user experience, and perform actions by delegating requests to a set of internet services.

    Application: HomePod is an intelligent home assistant, capable of handling everyday tasks — and controlling your smart home. It is powered by Apple Music and Apple Siri. SiriKit, the Apple Music API, Core ML and HomeKit can be used to link iOS apps to be used with HomePod.

Your application might be available on Google Play Store, Microsoft Store, or Apple App Store. However, if you haven’t started thinking about making your product accessible via platforms like Amazon Echo and Google Home, you are lagging behind.

Use Case for VUI

Think carefully about users and different use cases where VUI can be applied in your product. The most important question is "Will your users get any benefit if you add VUI in your product?". Adding a VUI just because it’s a trending technology is not the right approach at all. Some of the use cases include:

  • Adding Voice search to your help so that users can search content with voice
  • In an ecommerce application to browse catalogue easily just like talking to a salesperson in physical store. For instance, show me medium sized formal shirt in blue checks
  • In Auto form fill so that user can easily fill and submit large forms without using mobile keyboard
  • Integration with toolkit like Amazon Alexa, Google Assistant or Apple Siri to make your app accessible on VUI platforms

The Architecture, Design and UI of an application could be reworked and reimagined to fit this new paradigm of VUI. To add VUI in your app, you need a combination of two important technologies:

  • Automated Speech Recognition: An ASR tool translates user’s speech into text. Some of the popular paid speech recognition engines are Google Speech API, Microsoft’s Bing Speech API etc. A few free ASR tools include Voxforge, Cmusphinx, Web Speech API, Wit.ai etc. Amazon also provides toolset for ASR but it can be only used in developing skills for the Amazon Echo device.
  • Natural Language Understanding (NLU) is how you interpret the response returned by recognition engine.

Benefits by adding VUI

Adding VUI to make interaction with your existing graphical interfaces can be more convenient for your product users. Some of the direct benefits are:

  • Users do not need to follow a rigid structure so it is easier for them to interact with the product.
  • More natural, higher user acceptance of your product
  • With faster interaction, user can accomplish more tasks in a shorter time, thereby increasing productivity
  • Easy voice control removes possibility of getting lost in sub-menus

The technology of speech recognition has improved leaps and bounds in past few years. Now a days most of the mobile devices also support speech recognition with high accuracy. But it can only solve a part of the problem. What you do with the information, how do you go from recognizing the words to doing what users actually expect, requires a lot of efforts and brainstorming.

If you want Daffodil to help you in identifying the use cases in your product to take advantage of VUI or to develop Skills or Actions for your product, schedule a free 30 min consultation with our VUI expert, Twinkle Sharma.