Four Ways Conversational Interfaces Could Simplify Your Life
On the last day of SpeechTEK 2018, I had the pleasure of moderating a Sunrise Session entitled “The Future of Speech-Enabled Applications.” The goal of this roundtable was to brainstorm about creative and useful applications that could take conversational interactions to the next level.
More than a dozen attendees from a variety of backgrounds held a lively discussion and came up with four innovative ideas, which I have summarized in this article. First, let’s look at the underlying technologies and why we find them so fascinating.
Why We Love Conversational Interactions
Speech is the most natural way for humans to interact. Human infants quickly learn the power of the human voice to delight—and sometimes frustrate—their parents. The ways in which we use our voices is becoming much more diverse, thanks to the proliferation of AI-powered voice assistant platforms such as Alexa, Hey Google, and Cortana. For example, did you hear about the British baby whose first word was not “Mum” or “Dad”, but “Alexa”? Apparently, the baby heard his parents ask Alexa for help, and he figured out that he could get a reaction from her. Unfortunately, Alexa’s response was “Sorry, I didn’t get that,” suggesting that these devices probably will not replace human parents anytime soon.
Joking aside, it is no surprise that modern consumers who want a seamless, frictionless experience with products and brands often choose voice interactions. In contact centers, open-ended human like interactions through natural language interfaces allow customers to conduct business without the hassles of traditional IVRs. Conversational customer care uses Artificial Intelligence to drive conversations with unstructured conversational speech, rather than tedious and often frustrating directed and stilted machine-type dialog. Enterprises who deploy this technology see a significant increase in self-service usage and adoption as well as an improvement in customer experience.
Combining Visual with Voice
All of our roundtable participants agreed that pure voice-only devices will become obsolete in the near future. The next generation of these devices will incorporate video with voice, similar to Amazon’s Echo Show—but more robust. In addition, deep learning systems can identify and classify complex patterns in rich data, thereby replacing humans in many routine tasks that involve pattern recognition.
Our discussion group’s own personal experiences and pain points inspired these ideas:
- In-Home Medication Reminder—Do you have trouble remembering if you took your meds today? An app could use a sensor similar to the ones used in grocery store checkout lanes to measure the weight of your pill bottle compared to yesterday. If the bottle’s weight has not changed, your personal digital assistant could tell you that you need to take your meds.
- Clutter Organizer—Are you ready to stop procrastinating and finally organize your garage or attic? An app could enable you to catalog pictures of all your items (like Adobe Lightroom) and add voice text markers to them for easy sorting. This app would also come in handy if you are moving to a new space. You could use the voice tags to search for specific items.
- Searching Books and Articles—Visual searches can be tedious. An app could allow you to use voice to search for specific content. For example, if you were reading a historical novel, you could say, “Find Texas” and the app would identify all pages containing that word.
- Fitness—If your Fitbit is not already annoying enough, an app could enable you to carry on two-way conversations with your fitness tracking devices and receive voice reminders.
A World of Possibilities
Our discussion group just scratched the surface of the infinite possibilities for natural, human-like conversational interactions and how they can continue to simplify our lives—whether at home, at work, or at play. Artificial Intelligence still has a lot of room for improvement. (Just ask the British baby or anyone who has grown frustrated with their voice assistant.) In the near future, we can expect to see voice assistants grow smarter and more “human,” with the ability to analyze and respond to our emotions. It is an exciting time for conversational interaction technologies, and the more we use them, the more they will “learn” and continue to evolve. They (hopefully) will not render us useless, but they can definitely make our lives easier!
Despite in-depth online intelligence, many companies are still struggling to engage with customers. Can call analytics help?
Paco Nathan of O'Reilly Media's R & D Group discusses the benefits of natural-language processing (NLP) when working with text converted from video in this clip from his SpeechTEK 2018 keynote.
Even though experienced Voice User Interface (VUI) designers are hyper-sensitive to the importance of good localization over blind translation—and to the challenges of conversational automation in general—our UI team was surprised at the number of complex roadblocks we ran into when localizing a chatbot for our large international client. Read on to find out what you need to consider before undertaking a similar project.