Amazon Alexa & Voice User Experiences

Since it first arrived at my home nearly a year ago I have been hooked on the the Amazon Echo and the potential of voice based user experiences. This week I spent time in Seattle at Amazon HQ meeting with the Alexa partner team discussing everything from voice UX best practices, skills development for the Alexa and more.

Photo Jul 19, 9 07 00 AM

To recap, the Echo and it’s cloud supported voice based engine Alexa have been in development for the last 6 years. Since it’s initial launch the devices that comprise the echo ecosystem are regularly sold out and based on the nearly 40,000 stellar customer reviews  (4.5 stars) the experience is resonating with it’s users.

Photo Jul 19, 9 09 42 AM

The core of the experience is a combination of automated speech recognition, natural language processing and a cloud based AI that comprise a voice based user experience. Voice UX is another example of a conversational experience and will become pervasive over the next few years.

Photo Jul 19, 9 11 56 AM

As with most artificial intelligence entities, learning new skills is how personalized and contextual experiences will be created. With Alexa It is possible to “teach” alexa new conversational elements and interactions through developing skills.

Photo Jul 19, 9 26 05 AM

An analogy would be when Neo in the Matrix “learns” kung fu through a knowledge/skill upload. In a similar way Alexa may not be able to learn Kung Fu, at least not yet, but it is possible to build highly engaging voice based experiences.

f22c50f29387e1461274eb73ae3a329e97e3aa09ac8dffee9218e017cd6c8b99

Developing Skills for Alexa is one of the quickest ways for brands to connect with the rapidly growing audience that calls upon Alexa to empower their daily lives. Brands such as Dominos and Capital One have already launched skills to capitalize on being the first to own certain invocation phrases. With the Dominos skill a user can order a pizza and track their order through Alexa.

Screenshot 2016-07-21 15.27.44

Skills are comprised of a Skill Interface and a Skill Service. The Skill Interface is how the Voice User Experience is configured. This includes invocation and utterance phrases from the user as well as the mapping of intent schemas scored and resolved by the Skill Service. This is how Alexa is trained to resolve a users spoken word and connect it with a users intent and resolved into action.

Screenshot 2016-07-19 13.30.29

One of the benefits of Alexa is that the experiences can persist beyond a single session. Even though the experiences may seem ephemeral by nature, the fact is Skills can be created that persist across sessions. This could be hours or days.

Screenshot 2016-07-19 11.43.36

The other benefit is that all invocations and interactions are mapped to cards in the Alexa companion app. This is one way that brands can connect a skill interaction with mobile and digital campaigns.

Screenshot 2016-07-19 13.33.01

Other benefits for brands is that it is possible to deep link to skills within the Alexa companion app for those looking to connect omnichannel communication and messaging to drive discoverability of the skill.

One of the key points for brands to consider is the role being “first” can play when it comes to user invocation terms. Brands that align with non-trademarked terms such as “laundry” will be the first in the order of how skills are discovered. This is key as the Alexa engine expands beyond the Echo with Amazon Voice Services.

Photo Jul 19, 9 33 12 AM

Looking to the near future there will be 45 million connected homes by 2017 and connected car penetration will be over 60 million cars by 2020. The role that Alexa will play in the coming years will go well beyond the Echo, Dot, Tap & the Fire Stick and extend into other form factors through the portable Amazon Alexa Voice Service.

Photo Jul 19, 9 07 41 AM (1)

An example is the connected car partnership between Ford & Amazon to further connect Alexa. This is where the platform will create scale across the ever growing IOT ecosystem.

Ford

Future posts will cover emerging trends tied to Voice Based User Experiences such as the infinitely wide top level UI, definitive choices, automatic learning, proactive explanation as well as user punctuation. For additional questions or assistance with Alexa Skills please follow Tom Edwards @BlackFIn360

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s