Delivered at Casual Connect USA. Game developers often wonder what’s next. Is it AR? VR? One new technology we don’t need to wonder about is Voice Interfaces. Voice command interfaces aren’t a question of ‘if’ or ‘when’ anymore; they’re already happening. In this session you will hear about the most common (and amusing) traps developers fall into when designing audio interfaces and learn industry best practices for designing apps and games that work with voice services.

1. Designing Voice Driven Game
Experiences
David Isbitski
Chief Evangelist, Alexa and Echo
Amazon

2. Designing Voice Driven Game Experiences
DAVE ISBITSKI
CHIEF EVANGELIST, ALEXA AND ECHO
@TheDaveDev
isbitski@amazon.com

3. Voice Recognition
Natural Language Understanding
The key is in the interactions.

4. Key Design Principles for
VOICE INTERACTIONS
 Interactions Should Provide High Value
 An Interaction Should Evolve Over Time
 Users Can Speak to Your Service Naturally
and Spontaneously
 The Service Should Understand Most
Requests to Your Interface
 An Interface Should Respond in an
Appropriate Way

5. Interactions Should Provide High Value

6. HighUtility LowUtility
Doing
Performsa Task
“Alexa, askScoutto arm away mode.”
“Awaymode armed. You have 45 seconds
toleave thehouse.”
Searching
Identifiesspecificinfo
“Alexa, askVendorifthereare Pearl
Jam ticketsavailablefor this
weekend.”
“There area limitedamount oftickets,
ranging from$49 to $279.”
Telling
Providesa quick referencepoint
“Alexa, tellme acat fact.”
“It iswell known thatdogs aresuperiorto
cats.”
Browsing
Givesinfo ona broadsubject
“Alexa, askAmazon what’son sale.”
“The followingitemsare on sale right
now...”

7. Interactions Should Provide High Value
Voice is conversational. Very different than touch driven experiences. Less is
more.
Think of Voice as another UI to your game logic. Mobile, Web, Voice UI.
A large majority of the types of interactions today can grow with the user over
time. Aim for interactions that perform tasks on behalf of the user and learn
as time goes on.
This will provide a much better experience and lead to more interactions that
can do more.

8. An Interaction Should EvolveOverTime

9. W H E R E D O Y O U S T A R T ?
The Evolution of a Voice Experience
Traffic Example
Give an estimated time of
arrival from home to work.
Traffic Example
Include accidents, construction
and closures on route.
Traffic Example
Proactively alert user to delays
and provide alternate routes.
R U N
Evolve Over Time
C R A W L
What’s Your Core Functionality?
ANALYZE USER FEEDBACK
& OPTIMIZE
W A L K
Expand Capabilities & Features
INNOVATE FOR
CUSTOMERS

10. An Interaction Should Evolve Over Time
Voice user interfaces work well when they are focused, and give
quick responses.
Start with a primary use case that both communicates your business
case, but is also a clear winner for a voice user interface.
Let’s do one thing well, and add in capabilities allowing it to get
smarter over time.
Evolve shorter, more focused interactions by learning about the
customer.

11. Example of Adaptive Design
VOICE INTERACTION
Launch Travel Buddy
Hi, I’m travel buddy. I can easily tell you about your
daily commute. Let’s get you set up. Where are you
starting from?
Mountain View
Ok, and where are you going?
San Francisco
Great, now whenever you ask, I can tell you about
the commute from Mountain View to San Francisco.
The current commute time is one hour and twelve
minutes. There is a 15 minute delay on I280.
Launch Travel Buddy
Your commute time is currently fifty four minutes.

12. Users Can Speak to Your Interface Naturally and Spontaneously

13. Users Can Speak to Your Interface Naturally and Spontaneously
The experience of using your voice interaction should allow users to
not have to think about what to say and allow them to not remember
how to say it.
They should be able to converse with your interface just as they
would another human.
All they need is a rough idea of what your service can do (e.g.
playing music, placing a call, etc.), and they just ask the service to do
it.
This is the real value of voice interface, but this value can quickly
erode in an interaction that forces users to interact in unnatural ways.

14. Users Can Speak to Your Skill Naturally and Spontaneously
You should try to remove artificial interaction syntax and make
interactions as natural as possible.
Allowing your users to make simple requests without having to think
about the format those requests should be in, will create a much
better experience.

15. Example of Streamlined Voice
Gameplay Interaction
StarLanes – Space MMO, fully audio driven.
Support multiple methods of game-play in StarLanes.
Fighter, Merchant, and Scout.
No way to make one audio UI that supported all the
different gameplay usability.
Solution? Parallel games: StarLanes, StarTrade and
StarScout.
Each individual game will let you play out that style of
gameplay. Doesn’t have to explain all of the others.
The audio interface can be kept clean and simple.
Integration between them all can be done on the
back end.

16. Starting a Conversation in
Voice Interactions
Invocation options:
An invocation is how you start your voice service.
With Alexa, you can say:
“Alexa,
[ask | tell | play | launch | use | start |
begin] MyService
[for | to | and | for]
[variable]”
Alexa, ask [scheduleUpdate] for [dailyUpdate].
Alexa, start [scheduleUpdate].

17. Your Service Should Understand Most Requests

18. Your Service Should Understand Most Requests
In a natural voice interaction, most requests are understood and
acted on.
Your service should endeavor to do the same.
Requiring numerous attempts to invoke your service will be
frustrating for your customer.

19. An Interactions Should Respond in an Appropriate Way

20. Hello?

21. Voice Interactions with
Generated Characters
Voice is a natural, first UI for everyone.
Especially true in VR experiences
Create a Listening Model – recorded voice
responses based on intents of language
Pre-generated responses are ok
Push To Talk (PTT) or Keyword
Mechanical Turk – Human + AI real-time
responses

22. An Interaction Should Respond in an Appropriate Way
Voice is most natural way for us to communicate.
Provide adequate error handling for unexpected or unsupported
input.
A user should never be exposed directly to error handling.
Check for missing variables or values in your service.
If you find any missing information you should respond to the player
with a prompt for more details.

23. Having a Good Conversation in
an
AUDIO EXPERIENCE
 Makes It Clear that the User Needs to Respond
 Doesn’t Assume Users Know What to Do
 Clearly Presents the Options
 Keeps It Brief
 Avoids Overwhelming Users with Too Many
Choices
 Offers Help for Complex Experiences
 Asks Users Only Necessary Questions
 Uses Confirmations Selectively
 Obtains One Piece of Information at a Time
 Makes Sure Users Know They are in the Right
Place
 Avoids Technical and Legal Jargon
Write for the Ear, not the Eye!

24. Digging Deeper into Voice Design
Alexa Skills Kit Voice Design Best Practices - http://bit.ly/voicedesign
Alexa Skills Kit Voice Design Handbook - http://bit.ly/voicehandbook
Wired for Speech: How Voice Activates and Advances the Human-
Computer Relationship, by Nass and Brave
The Elements of VUI Style: A Practical Guide to Voice User Interface
Design, by Bouzid and Ma
Don’t Make Me Tap!: A Common Sense Approach to Voice Usability, by
Bouzid and Ma
The Voice in the Machine: Building Computers That Understand Speech,
by Pieraccini
Voice User Interface Design, by Cohen, Giangola, and Balogh

25. Designing Voice Driven Game Experiences
DAVE ISBITSKI
CHIEF EVANGELIST, ALEXA AND ECHO
@TheDaveDev
isbitski@amazon.com