Designing your first voice interface (workshop)

B6031b692931f4f7b7a6a8370316daf7?s=47 bensauer
June 09, 2017

Designing your first voice interface (workshop)

Learn about the voice design process, get busy crafting dialogue, learn some fundamental principles, design and test and voice interface in a team. You'll see just how different the design methods are, and what the 'Wizard of Oz' testing method is. Come find your inner bot!

B6031b692931f4f7b7a6a8370316daf7?s=128

bensauer

June 09, 2017
Tweet

Transcript

  1. Design your first voice interface Product Camp Poland 2017 •

    Ben Sauer
  2. Organise
 into teams of 4 *each team needs a MacBook

    *your packet has more instructions
  3. Welcome

  4. Today

  5. Warmup

  6. A spectrum 
 of responses

  7. The medium you design in is not the medium you

    experience
  8. Find out what doesn’t work, as well as what does

  9. “When is the next train to London Victoria?” Too concise:

    
 20 minutes.
  10. “When is the next train to London Victoria?” Too detailed:

    
 The next train from Brighton station to London Victoria station leaves in twenty minutes, at twenty past ten. It has no first class service and divides at Haywards Heath. It arrives at London Victoria at ten past eleven.
  11. “When is the next train to London Victoria?” Just right:

    
 The next train from Brighton to London Victoria leaves in 20 minutes.
  12. VOICE INTERFACES: NOW AND BEYOND

  13. ARISTOTLE There is only one condition in which we can

    imagine managers not needing subordinates, and masters not needing slaves. This condition would be that each instrument could do its own work, at the word of command or by intelligent anticipation. @bensauer
  14. VUI = Voice User Interface ASR = Automatic Speech Recognition

    NLU = Natural Language Understanding @bensauer humans  and   machines  talking turning  speech   into  words turning  words   into  meaning
  15. None
  16. Curious Rituals produced by The Near Future Laboratory

  17. None
  18. Curious Rituals produced by The Near Future Laboratory

  19. None
  20. • Limited shared vocabulary • Poor skills / co-ordination •

    No capacity to learn • Never sure job will get done • Turns you into the a$$h0le Using VUI is a bit like dealing with Manuel…
  21. https://www.flickr.com/photos/cryptik/23815673664 @bensauer ?

  22. Our true calling is to make 
 the system fail

    gracefully.
  23. REALITIES OF VUI

  24. VUI is deceptively limited. @bensauer

  25. @bensauer VUI USE MAY BE U-SHAPED @bensauer AWESOME SUCKS 10

    100 ∞ USE CASES
  26. None
  27. Platforms limit possibilities. @bensauer

  28. Transactions over conversations. @bensauer

  29. The context of use 
 is everything.

  30. WHERE IS 
 VUI GOING?

  31. The price of a multifunctional touchscreen 
 is the volume

    of required input. VUI is an efficient shortcut. @bensauer
  32. The short-term promise of VUI is to simplify complex interactions

    into directly expressed goals, without the distraction of a screen. @bensauer
  33. @bensauer BEYOND USE CASES “If the doorbell rings while I’m

    in the garden, call me.” @bensauer
  34. None
  35. None
  36. None
  37. @bensauer @bensauer VOICE ASSISTANT CONCEPTS SIRI: ’FAMILIAR’ ALEXA: ’THING’ http://www.dfki.de/LAMDa/2013/accepted/13_ApplinFischer.pdf

  38. @bensauer AMAZON’S PLAY FOR UBICOMP • TVs (Westinghouse, Element, Seiki)

    • Fridges (LG) • Home robots (LG) • Wifi speakers (Lenovo) • Kid’s speaker (Mattel) • Lamps (GE) @bensauer • Alarm clocks • Cars (Ford, VW) • Charging docks • Watches • Cameras • Smartphones (Huawei)
  39. @bensauer CONVERSATIONAL UI IS PRETTY HYPED @bensauer WTF!  menus!

  40. AI is getting too much hype.

  41. WHAT IS CONVERSATION?

  42. Context Language Exchange Agreement Transaction / Action

  43. from Paul Pangaro's ‘Conversation is more than interface’ https://vimeo.com/207866146

  44. WHAT’S DIFFERENT ABOUT VUI DESIGN?

  45. Recall over recognition.

  46. The first interaction 
 expresses the goal.

  47. GUI VUI THE USER JOURNEY

  48. The medium you design in
 is not the medium you

    experience. @bensauer
  49. Shorter ‘Time to Test’.

  50. A.I. is getting better at understanding so that 
 we

    don’t have to.
  51. The heart of VUI is great writing. @bensauer

  52. VUI OPPORTUNITIES

  53. @bensauer VUI APPS @bensauer

  54. @bensauer SEARCH RESULTS (IN APP) @bensauer

  55. @bensauer SIMPLE GOPHER TASKS @bensauer

  56. @bensauer PLAYING WITH AMAZON ECHO @bensauer Raspberry Pi + Image

    + Lambda + Node Sayspring
  57. Our focus Design, prototype, and test a voice interface

  58. Our focus Ignore the technology!

  59. Our focus Use a 
 wake word

  60. Use cases s

  61. A great VUI starts with a great use case

  62. Speed, simplicity, convenience

  63. #1 Answer off the top of your head

  64. What time is it? What’s the weather? Is there a

    conference dinner tonight?
  65. #2 A way to avoid pulling out a phone or

    jotting notes on paper
  66. Set a timer for for 20 minutes Call Anna

  67. Order a pizza from Tramonti’s Remind me to make a

    dentist appointment tomorrow
  68. #3 Help for someone with their eyes or hands occupied

  69. How long will I be in traffic? How many cups

    of sugar do I add?
  70. Alert people to helpful information Bonus

  71. Hey Google, what’s up? There’s a 40 minute delay on

    Highway 17
  72. Activity: 
 find a use case

  73. Step #1
 Pick a decider for today

  74. Step #2
 Write down activities you do most weeks One

    activity per post it Swimming Cooking Drive  to  work Take  kids  to   school
  75. Step #3
 Map your week as a group Commute Work

    Lunch Gym MONDAY Commute W TUESDAY
  76. Step 4: Write down questions or tasks that a voice

    interface could help with Drive  to  work Check   traffic Shopping Find  shelf   location Getting   dressed Check   weather Dinner Ordering   takeout
  77. Dinner Ordering   takeout Step 5: Vote for your favourites

    Drive  to  work Check   traffic Shopping Find  shelf   location Getting   dressed Check   weather ✓ ✓ ✓ ✓ ✓
  78. Step #6 Choose your idea

  79. Step #7 Empathise Feeling  tired Hands  dirty Kids   screaming

    Make   healthy,  easy,   tasty  food Cooking   dinner
  80. Personality

  81. Same voice, different roles

  82. Users hear personality, regardless

  83. Example: Cortana Confident, caring, competent, loyal Helpful, but not bossy

    Functionally and emotionally transparent
  84. Define personality

  85. Step #1
 Discuss and capture Page 4 of the handout

  86. Breaktime! Come back at 11

  87. What do people say first? Define personality

  88. What they say,
 and the way they say it

  89. None
  90. None
  91. None
  92. None
  93. Activity: 
 capture the first question

  94. Step #1
 Open a google doc Give it the following

    section headings: •Test Brief •Opening questions •Sample dialogue (1,2,3,4)
  95. Step #2
 Write a test brief

  96. Step #3
 Write a first sentence “Alexa,  find  me  a

     steak   restaurant  in  Gdansk.”
  97. Step #4
 Choose roles •A moderator •A participant from another

    team
  98. Step #5
 Capture the first question

  99. Step #6
 Swap roles and repeat

  100. Step #7
 Swap roles and repeat

  101. Sample dialogue Define personality

  102. Dialogue format

  103. Expressing personality

  104. Find the best paths

  105. Exercise Creating dialogue

  106. Step #1
 Choose roles • A user • The voice

    interface • One or two transcribers
  107. Step #2
 Improvise! No more than six to ten 


    lines of dialogue
  108. Step #3
 Write your own

  109. Step #4
 Share and discuss

  110. WOZ demo time

  111. Lunch! See you at 13:30pm

  112. Exercise 6 Editing dialogue

  113. Principles

  114. Sound natural

  115. Be true to your personality

  116. Give people credit

  117. Be cooperative

  118. Keep it short What’s the temperature?

  119. Keep it short How old is Prince Harry?

  120. Prince Harry is 32 years old He’s 32 years old

    32
  121. Take turns

  122. Bonus tips

  123. #1 Use pronouns

  124. #2 Important information 
 at the end

  125. #3 Say everything 
 out loud

  126. Exercise: 
 editing dialogue

  127. Goal: 
 make it good, 
 make it testable

  128. Step #1
 Edit in pairs

  129. Step #2
 Identify patterns The  user  starts   the  recording

      defining  the   duration The  user  starts   the  recording   *without*  defining  a   duration The  user  stops  the   recording The  user  plays   back  the  meeting Example: Recording meetings
  130. Step #3
 Setup ‘Say Wizard’ see handout page 8 tip:

    make text bigger with 
 Shift cmd +
  131. Step #4
 Copy dialogue into script.txt

  132. Step #5
 Remove the user’s lines from script.txt

  133. Step #6
 Reorder the dialogue

  134. First answer Second Third Fourth Second 
 scenario

  135. Step #6
 Reorder the dialogue tip: leave gaps

  136. Wizard of Oz Testing

  137. The goal: Having all the answers

  138. Fail fast, Fail cheap

  139. Amazon Echo Early design process

  140. The WOZ process

  141. Exercise Wizard of Oz testing

  142. Step #1
 Choose roles •A wizard •A participant from another

    team •Two observers
  143. Step #2
 Run the test

  144. What did you learn?

  145. Step #3
 Reflect & Refine

  146. Step #4
 Swap roles and test

  147. Step #5
 Reflect & Refine

  148. Final test
 Record a video

  149. How was it?
 Record a video

  150. Post-test survey Annoying Useful Classic Futuristic

  151. Dialogue Flow booking 
 a cab

  152. Exercise: Map the flow tip: don’t re-use the 
 dialogue

    as titles
  153. Build and test

  154. UTTERANCE “Order me some glow-in-the-dark toilet paper.”

  155. 
 
 “Order me a Nintendo Switch.” INTENT Buy Product

  156. 
 
 “Set a timer for 30 seconds.” VARIABLE Timer

    Duration
  157. VUI PRINCIPLES

  158. Always be capturing.

  159. Postel’s Law Be conservative in what you send, be liberal

    in what you accept. @bensauer
  160. I’d really like to visit Llanfairpwllgwyngyll- gogerychwyrndrobwllllantysiliogogogoch. @bensauer USER: In

    North Wales? ALEXA:
  161. Design for mundane realities.

  162. Pair Bluetooth!!!! @bensauer HEAVILY ACCENTED USER FOR THE 3RD TIME:

    I’m really sorry, I still don’t understand. Can I suggest using the Alexa app instead? ALEXA:
  163. Considerate confirmation.

  164. Did you mean Odeon, Brighton? @bensauer SYSTEM HAS 50% CONFIDENCE:

    When would you like to go to 
 the Odeon Brighton? IMPLICIT: <Lights switch on> NONE:
  165. Human, but not *too* human.

  166. None
  167. RESOURCES • Cathy Pearl’s VUI book • Wizard of Oz

    Testing:
 https://chatbotsmagazine.com/stfu-test-your- voice-app-idea-in-less-than-an- hour-2638cdff2503 • Say Wizard:
 https://github.com/bensauer/saywizard
  168. MARC WEISER “The most profound technologies are those that disappear.

    They weave themselves into the fabric of everyday life until they are indistinguishable from it.” @bensauer
  169. Questions? Get in touch! ben@clearleft.com @bensauer

  170. Give me feedback As a team, write two words on

    post- its that describe your workshop experience today and leave them behind on your table.