SlideShare a Scribd company logo
1 of 57
ALGOLIA WEBINAR
Voice Search Lessons
71%
Voice Usage
32%search via voice daily
would rather use voice than
keyboard to search
PWC
Voice doesn’t have to be a back-
and-forth
Voice doesn’t have to be a back-
and-forth
(though it can be)
Alexa and Google Assistant are only
part of voice
Alexa and Google Assistant are only
part of voice
(Don’t forget mobile)
Voice-Only
Voice in,
voice out.
Levels of Voice
Voice-First
Voice is the primary mode.
Voice-Added
Voice is just one input or
output mechanism.
Voice-Only
Voice in,
voice out.
Levels of Voice
Voice-First
Voice is the primary mode.
Voice-Added
Voice is just one input or
output mechanism.
Input and Output Precision
The right result, for the right user,
at the right time, presented in the
right way.
“It [was] obvious that there were
major design flaws. Callers over the
telephone were overwhelmed by the
same volume and organization of mail
headers that worked so effectively in
the graphical interface.”
From the book Voice Interaction Design
Default
Solutions
“You get what you pay for” is true here, too.
LIMITED
But, hey, it’s free
iOS/Android
Alexa/Google Assistant
Google Chrome
Speech to Text
Established
Providers
MORE CONTROL
With a cost
Google Cloud
Watson Speech to Text
Twilio
Up and
Comers
UNIQUE APPROACH
Assembly AI
Snips
What To Do With the Query?
There Will Be
Misunderstanding
Speech-to-Text Isn’t Perfect
The best speech-to-text hovers just over 95% accurate; this is better than humans
but not as precise as typing.
There Will Be
Misunderstanding
“What’s the latest email
from
Mark Dwayne?”
There Will Be
Misunderstanding
Speech-to-Text Isn’t Perfect
The best speech-to-text hovers just over 95% accurate; this is better than humans
but not good enough.
Searchable Items Are Enums
They represent a constrained set of items, which cause problems when a user looks
for something different outside that list.
There Will Be
Misunderstanding
Senders
Lizzy Carl
Y. L. Stiff
Mark Dwayne
Lorenzo Gomez
Lisa Fong
Emmanuelle Smith
Amy Hall
Michael Banian
Emilie Pulisic
“What’s the latest
email from Mark
Twain?”
There Will Be
Misunderstanding
Speech-to-Text Isn’t Perfect
The best speech-to-text hovers just over 95% accurate; this is better than humans
but not good enough.
Searchable Items Are Enums
They represent a constrained set of items, which cause problems when a user looks
for something a little different.
Nonetheless, A Match Must be Found
Let’s examine some commonly recommended approaches...
“Hey, you’ve gotta use fuzzy
matching.”
What… Is Fuzzy
Matching?
Phonetic Algorithms
These algorithms transform words into approximate phonetic representations.
A sample:
● Soundex
● Fuzzy Soundex
● Lein
● Metaphone
● Double Metaphone
● Metaphone 3 (commercially licensed)
● NYSIIS
● ONCA
● Roger Root
● Phonex
Different Encodings
350TWN1111111 D500
TWN
DWAYN
DWAN D5
01200000000000TND200
01200
376000 DWN
What… Is Fuzzy
Matching?
Levenshtein Distance
Also known as the “minimum edit distance.”
Represents the minimum number of edits needed to change one string (i.e. “word”)
into another.
How It Works: Levenshtein Distance
CALCULATE
THE MINIMUM
NUMBER OF EDITS
NECESSARY
Dwayne
Twayne
Twayne
Twayne
Twaine
Twaine
Twain_
Twain
0
1
1
1
2
2
3
3
Banian
Tanian
Twanian
Twanian
Twa_ian
Twa_ian
Twa_i_n
Twain
0
1
2
2
3
3
4
4
Okay,
let’s stop assuming.
Let’s test it.
4
The
Experiment
1
2
3
Phoneticize all attributes across all
records for all algorithms
Create a list of 20 queries
Run queries with real people, with each
algorithm, with levenshtein distance
Have them specify which results (1 per
algorithm) are relevant
Algorithm Performance
THE RAW TEXT
CONSISTENTLY
OUT-PERFORMED
EVERY
ALGORITHM
Algorithm Performance
OVER 75%
ACCURACY
WITHOUT
RELEVANCE
OPTIMIZATION
Then… How Do We
Build Relevance?
“Find me this week’s emails
about the latest budget proposal
from my team.”
Our initial query
“Find me this week’s emails
about the latest budget proposal
from my team.”
Remove inconsequential (stop)
words
Filter First
100%
The entire
haystack
A filtered, more
manageable
haystack
[
How to
Reduce the
Haystack
1
2
3
Look for filterable values in query
Apply personalization
Take overall context
Filterable Values
In Spoken Queries
To Find Result
Slot Values From NLU
Slot values sent directly from Alexa, Dialogflow, etc.
Query Scanning
Simplest option, works well without NLU, but can be a bit blunt force.
I.e. does this query have a filterable value?
Built-in Search Engine Tooling
For example, Algolia’s query rules which apply filters or other rules from free-form
textual queries
const colors = [`red`, `blue`, `green`];
query = query.toLowercase();
const matched = colors.filter(color => {
query.indexOf(color) !== -1;
});
“Find me this week’s emails
about the latest budget proposal
from my team.”
Filter to reduce searchable items
type:emails
Personalization
and
Context
for
Voice Search
The Right Result for the Right User
Use the users’ affinities to filter results, further reducing the haystack.
Most search engines can “boost” results rather than filtering so you don’t reduce the
searchable records too far.
At the Right Time
Contextual information can filter or boost.
Information such as:
● Recent requests
● Time or date
● Number of user requests
“Find me this week’s emails
about the latest budget proposal
from my team.”
sent_before:now
sent_after:Sunday
team_id:9
Filter to reduce searchable items
type:emails
Analytics
and
Synonyms
for
Voice Search
Analytics
People are going to use different words for the same concept (pop, soda, Coke).
Prep goes a long way, but there’s no prep and assumptions that’s better than data.
Synonyms
Synonyms allow a user to search with one term, but match another equivalent term.
Raw Performance
STT Correctly
Understood
and Good
Result
Overall Good
Result
Analytics
and
Synonyms
for
Voice Search
Analytics
People are going to use different words for the same concept (pop, soda, Coke).
Prep goes a long way, but there’s no prep and assumptions that’s better than data.
Speech to text will also misunderstand people; that needs to be handled.
Synonyms
Synonyms allow a user to search with one term, but match another equivalent term.
These can “mean the same thing,” or correct for errors.
“Find me this week’s emails
about the latest proposal
from my team.”
sent_before:now
sent_after:Sunday
team_id:9
Filter to reduce searchable items
type:email
budget
spending
Probably more
than one result,
so you need
some way to
pick the best
Sort them, then
take what you
need
Sort by what’s
important.
Maybe the
latest?
Subject Sent
RE: RE: Budget Proposal for Q3 Today
RE: RE: RE: RE: Budget Proposal for Q3 Today
Question on your budget proposal Last week
2016 budget proposal 2 years ago
RE: Budget Proposal for Q3 Yesterday
Sort by what’s
important.
Maybe the
latest?
Subject Sent
RE: RE: Budget Proposal for Q3 Today
RE: RE: RE: RE: Budget Proposal for Q3 Today
RE: Budget Proposal for Q3 Yesterday
Question on your budget proposal Last week
2016 budget proposal 2 years ago
↓
Then grab all
you need.
(Voice-first
often needs just
one result.)
Subject Sent
RE: RE: Budget Proposal for Q3 Today
RE: RE: RE: RE: Budget Proposal for Q3 Today
RE: Budget Proposal for Q3 Yesterday
Question on your budget proposal Last week
2016 budget proposal 2 years ago
↓
Train the User to
Reduce the
Haystack
Understand What’s Best Understood
Some terms are better understood by speech to text than others.
“Turn off (on?) the lights”
“Turn out the lights”
You’ll discover this in your testing and in your analytics.
People Respond In-Kind
People will respond with the same vocabulary as their conversation partners.
Be consistent in the output to guide users to the more understandable word choices.
But What If There Is
No Perfect Result?
No Good Results?
Do You Really Want to Show Results?
Sometimes, asking for clarification is better than showing a best guess.
Sometimes, show a best guess is better than asking for clarification.
Different Answer for Different Use Cases
Different use cases have a different level of tolerance for best guess
“How easy is it to back out of this choice?” “Will any damage be done?”
Different Media, Different Choices
The input and output influence the decision, too.
Media
1
2
3
Voice-Only
Voice-First
Voice-Added
Voice-Added and Voice-First
VOICE-ADDED VOICE-FIRST
Voice-Added and Voice-First
VOICE-ADDED
Aides the user in achieving a goal on-screen; the user can
always fall back to the screen when voice is unsuited to
the task.
Can better handle “close” matches.
Voice-Added and Voice-First
VOICE-FIRST
Voice is the primary (or only) input and output
mechanism. Less precision than with a display and
keyboard input.
Voice-Added and Voice-First
VOICE-FIRST
Return just the right information.
The right information for that customer, for that time, for
that query.
Easily allow customer to make corrections.
“Find me this week’s emails
about the latest proposal
from my team.”
sent_before:now
sent_after:Sunday
team_id:9
Mark every word that’s left optional
Sort by number of matching words
type:email
budget
spending
Natural Language Queries
Better Analytics
Optional Words
Remove Stop Words
Faceting
Ignore Plurals
Personalization
Recent Context
Interaction Insights Context Usage
Relevance
Takeaways
Takeaways
Levenshtein Distance Yes; Phonetic Algorithms No
Levenshtein distance is a low-cost way to improve relevance
Synonyms to handle variety or misunderstandings further improve results
Reduce the Haystack
Use filters within the spoken query, plus personalization and context
Decide If This Calls For a Result
Voice-added experiences are more tolerant of approximate results
Voice-first and voice-only call for user confirmation and clarification
Thank you!
algolia.com/solutions/voice-search
CONFIDENTIAL

More Related Content

Similar to Voice search lessons

Principles & ux_systems
Principles & ux_systemsPrinciples & ux_systems
Principles & ux_systemsuxpin
 
Technical Writing For Consultants
Technical Writing For ConsultantsTechnical Writing For Consultants
Technical Writing For Consultantsrlucera
 
Module 8: Natural language processing Pt 1
Module 8:  Natural language processing Pt 1Module 8:  Natural language processing Pt 1
Module 8: Natural language processing Pt 1Sara Hooker
 
Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...
Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...
Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...Click Consult (Part of Ceuta Group)
 
Speech recognition an overview
Speech recognition   an overviewSpeech recognition   an overview
Speech recognition an overviewVarun Jain
 
Comu346 lecture 7 - user evaluation
Comu346   lecture 7 - user evaluationComu346   lecture 7 - user evaluation
Comu346 lecture 7 - user evaluationDavid Farrell
 
Getting Started with Voice UI
Getting Started with Voice UIGetting Started with Voice UI
Getting Started with Voice UIIsidore Gotto
 
Speak Up! Build an Alexa Skill for a Cause
 Speak Up! Build an Alexa Skill for a Cause Speak Up! Build an Alexa Skill for a Cause
Speak Up! Build an Alexa Skill for a CauseNikki Clark
 
KWFinder Review
KWFinder ReviewKWFinder Review
KWFinder ReviewNoel Peter
 
Become a good speaker
Become a good speakerBecome a good speaker
Become a good speakerSanoy Jacob
 
Become a goodspeaker
Become a goodspeakerBecome a goodspeaker
Become a goodspeakerhappyever
 
Become A Good Speaker
Become A Good SpeakerBecome A Good Speaker
Become A Good Speaker金 失成
 
Become a goodspeaker
Become a goodspeakerBecome a goodspeaker
Become a goodspeakerSanoy Jacob
 
Become a goodspeaker
Become a goodspeakerBecome a goodspeaker
Become a goodspeakerhappyever
 
iTalk: Using Technology as a Transitional Communication Tool
iTalk: Using Technology as a Transitional Communication TooliTalk: Using Technology as a Transitional Communication Tool
iTalk: Using Technology as a Transitional Communication ToolDamesMaddox
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processingpunedevscom
 
Aardvark case study from #sllconf by Max Ventilla and Damon Horowitz
Aardvark case study from #sllconf by Max Ventilla and Damon HorowitzAardvark case study from #sllconf by Max Ventilla and Damon Horowitz
Aardvark case study from #sllconf by Max Ventilla and Damon HorowitzEric Ries
 

Similar to Voice search lessons (20)

Principles & ux_systems
Principles & ux_systemsPrinciples & ux_systems
Principles & ux_systems
 
Technical Writing For Consultants
Technical Writing For ConsultantsTechnical Writing For Consultants
Technical Writing For Consultants
 
Voice Tech TO #1
Voice Tech TO #1Voice Tech TO #1
Voice Tech TO #1
 
Module 8: Natural language processing Pt 1
Module 8:  Natural language processing Pt 1Module 8:  Natural language processing Pt 1
Module 8: Natural language processing Pt 1
 
Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...
Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...
Understanding Alexa Skills: How to Add Amazon’s Market-Leading Device Into Yo...
 
Speech recognition an overview
Speech recognition   an overviewSpeech recognition   an overview
Speech recognition an overview
 
Comu346 lecture 7 - user evaluation
Comu346   lecture 7 - user evaluationComu346   lecture 7 - user evaluation
Comu346 lecture 7 - user evaluation
 
Getting Started with Voice UI
Getting Started with Voice UIGetting Started with Voice UI
Getting Started with Voice UI
 
Alabot
AlabotAlabot
Alabot
 
Speak Up! Build an Alexa Skill for a Cause
 Speak Up! Build an Alexa Skill for a Cause Speak Up! Build an Alexa Skill for a Cause
Speak Up! Build an Alexa Skill for a Cause
 
KWFinder Review
KWFinder ReviewKWFinder Review
KWFinder Review
 
Become a good speaker
Become a good speakerBecome a good speaker
Become a good speaker
 
Become a goodspeaker
Become a goodspeakerBecome a goodspeaker
Become a goodspeaker
 
Become A Good Speaker
Become A Good SpeakerBecome A Good Speaker
Become A Good Speaker
 
Become a goodspeaker
Become a goodspeakerBecome a goodspeaker
Become a goodspeaker
 
Become a goodspeaker
Become a goodspeakerBecome a goodspeaker
Become a goodspeaker
 
iTalk: Using Technology as a Transitional Communication Tool
iTalk: Using Technology as a Transitional Communication TooliTalk: Using Technology as a Transitional Communication Tool
iTalk: Using Technology as a Transitional Communication Tool
 
Tifle.Week1
Tifle.Week1Tifle.Week1
Tifle.Week1
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 
Aardvark case study from #sllconf by Max Ventilla and Damon Horowitz
Aardvark case study from #sllconf by Max Ventilla and Damon HorowitzAardvark case study from #sllconf by Max Ventilla and Damon Horowitz
Aardvark case study from #sllconf by Max Ventilla and Damon Horowitz
 

Recently uploaded

The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfThe Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfkalichargn70th171
 
Professional Resume Template for Software Developers
Professional Resume Template for Software DevelopersProfessional Resume Template for Software Developers
Professional Resume Template for Software DevelopersVinodh Ram
 
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideBuilding Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideChristina Lin
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...gurkirankumar98700
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...ICS
 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionSolGuruz
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVshikhaohhpro
 
Cloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStackCloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStackVICTOR MAESTRE RAMIREZ
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsArshad QA
 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxbodapatigopi8531
 
Test Automation Strategy for Frontend and Backend
Test Automation Strategy for Frontend and BackendTest Automation Strategy for Frontend and Backend
Test Automation Strategy for Frontend and BackendArshad QA
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Modelsaagamshah0812
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfjoe51371421
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providermohitmore19
 
What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number SystemsJheuzeDellosa
 
Active Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdfActive Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdfCionsystems
 
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsAlberto González Trastoy
 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerThousandEyes
 
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...soniya singh
 

Recently uploaded (20)

The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfThe Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
 
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
 
Professional Resume Template for Software Developers
Professional Resume Template for Software DevelopersProfessional Resume Template for Software Developers
Professional Resume Template for Software Developers
 
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideBuilding Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with Precision
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
 
Cloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStackCloud Management Software Platforms: OpenStack
Cloud Management Software Platforms: OpenStack
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptx
 
Test Automation Strategy for Frontend and Backend
Test Automation Strategy for Frontend and BackendTest Automation Strategy for Frontend and Backend
Test Automation Strategy for Frontend and Backend
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Models
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdf
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
 
What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number Systems
 
Active Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdfActive Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdf
 
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
 
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
 

Voice search lessons

  • 2. 71% Voice Usage 32%search via voice daily would rather use voice than keyboard to search PWC
  • 3. Voice doesn’t have to be a back- and-forth
  • 4. Voice doesn’t have to be a back- and-forth (though it can be)
  • 5. Alexa and Google Assistant are only part of voice
  • 6. Alexa and Google Assistant are only part of voice (Don’t forget mobile)
  • 7. Voice-Only Voice in, voice out. Levels of Voice Voice-First Voice is the primary mode. Voice-Added Voice is just one input or output mechanism.
  • 8. Voice-Only Voice in, voice out. Levels of Voice Voice-First Voice is the primary mode. Voice-Added Voice is just one input or output mechanism. Input and Output Precision
  • 9. The right result, for the right user, at the right time, presented in the right way.
  • 10. “It [was] obvious that there were major design flaws. Callers over the telephone were overwhelmed by the same volume and organization of mail headers that worked so effectively in the graphical interface.” From the book Voice Interaction Design
  • 11. Default Solutions “You get what you pay for” is true here, too. LIMITED But, hey, it’s free iOS/Android Alexa/Google Assistant Google Chrome Speech to Text Established Providers MORE CONTROL With a cost Google Cloud Watson Speech to Text Twilio Up and Comers UNIQUE APPROACH Assembly AI Snips
  • 12. What To Do With the Query?
  • 13. There Will Be Misunderstanding Speech-to-Text Isn’t Perfect The best speech-to-text hovers just over 95% accurate; this is better than humans but not as precise as typing.
  • 14. There Will Be Misunderstanding “What’s the latest email from Mark Dwayne?”
  • 15. There Will Be Misunderstanding Speech-to-Text Isn’t Perfect The best speech-to-text hovers just over 95% accurate; this is better than humans but not good enough. Searchable Items Are Enums They represent a constrained set of items, which cause problems when a user looks for something different outside that list.
  • 16. There Will Be Misunderstanding Senders Lizzy Carl Y. L. Stiff Mark Dwayne Lorenzo Gomez Lisa Fong Emmanuelle Smith Amy Hall Michael Banian Emilie Pulisic “What’s the latest email from Mark Twain?”
  • 17. There Will Be Misunderstanding Speech-to-Text Isn’t Perfect The best speech-to-text hovers just over 95% accurate; this is better than humans but not good enough. Searchable Items Are Enums They represent a constrained set of items, which cause problems when a user looks for something a little different. Nonetheless, A Match Must be Found Let’s examine some commonly recommended approaches...
  • 18. “Hey, you’ve gotta use fuzzy matching.”
  • 19. What… Is Fuzzy Matching? Phonetic Algorithms These algorithms transform words into approximate phonetic representations. A sample: ● Soundex ● Fuzzy Soundex ● Lein ● Metaphone ● Double Metaphone ● Metaphone 3 (commercially licensed) ● NYSIIS ● ONCA ● Roger Root ● Phonex
  • 20. Different Encodings 350TWN1111111 D500 TWN DWAYN DWAN D5 01200000000000TND200 01200 376000 DWN
  • 21. What… Is Fuzzy Matching? Levenshtein Distance Also known as the “minimum edit distance.” Represents the minimum number of edits needed to change one string (i.e. “word”) into another.
  • 22. How It Works: Levenshtein Distance CALCULATE THE MINIMUM NUMBER OF EDITS NECESSARY Dwayne Twayne Twayne Twayne Twaine Twaine Twain_ Twain 0 1 1 1 2 2 3 3 Banian Tanian Twanian Twanian Twa_ian Twa_ian Twa_i_n Twain 0 1 2 2 3 3 4 4
  • 24. 4 The Experiment 1 2 3 Phoneticize all attributes across all records for all algorithms Create a list of 20 queries Run queries with real people, with each algorithm, with levenshtein distance Have them specify which results (1 per algorithm) are relevant
  • 25. Algorithm Performance THE RAW TEXT CONSISTENTLY OUT-PERFORMED EVERY ALGORITHM
  • 27. Then… How Do We Build Relevance?
  • 28. “Find me this week’s emails about the latest budget proposal from my team.” Our initial query
  • 29. “Find me this week’s emails about the latest budget proposal from my team.” Remove inconsequential (stop) words
  • 30. Filter First 100% The entire haystack A filtered, more manageable haystack [
  • 31. How to Reduce the Haystack 1 2 3 Look for filterable values in query Apply personalization Take overall context
  • 32. Filterable Values In Spoken Queries To Find Result Slot Values From NLU Slot values sent directly from Alexa, Dialogflow, etc. Query Scanning Simplest option, works well without NLU, but can be a bit blunt force. I.e. does this query have a filterable value? Built-in Search Engine Tooling For example, Algolia’s query rules which apply filters or other rules from free-form textual queries const colors = [`red`, `blue`, `green`]; query = query.toLowercase(); const matched = colors.filter(color => { query.indexOf(color) !== -1; });
  • 33. “Find me this week’s emails about the latest budget proposal from my team.” Filter to reduce searchable items type:emails
  • 34. Personalization and Context for Voice Search The Right Result for the Right User Use the users’ affinities to filter results, further reducing the haystack. Most search engines can “boost” results rather than filtering so you don’t reduce the searchable records too far. At the Right Time Contextual information can filter or boost. Information such as: ● Recent requests ● Time or date ● Number of user requests
  • 35. “Find me this week’s emails about the latest budget proposal from my team.” sent_before:now sent_after:Sunday team_id:9 Filter to reduce searchable items type:emails
  • 36. Analytics and Synonyms for Voice Search Analytics People are going to use different words for the same concept (pop, soda, Coke). Prep goes a long way, but there’s no prep and assumptions that’s better than data. Synonyms Synonyms allow a user to search with one term, but match another equivalent term.
  • 37. Raw Performance STT Correctly Understood and Good Result Overall Good Result
  • 38. Analytics and Synonyms for Voice Search Analytics People are going to use different words for the same concept (pop, soda, Coke). Prep goes a long way, but there’s no prep and assumptions that’s better than data. Speech to text will also misunderstand people; that needs to be handled. Synonyms Synonyms allow a user to search with one term, but match another equivalent term. These can “mean the same thing,” or correct for errors.
  • 39. “Find me this week’s emails about the latest proposal from my team.” sent_before:now sent_after:Sunday team_id:9 Filter to reduce searchable items type:email budget spending
  • 40. Probably more than one result, so you need some way to pick the best
  • 41. Sort them, then take what you need
  • 42. Sort by what’s important. Maybe the latest? Subject Sent RE: RE: Budget Proposal for Q3 Today RE: RE: RE: RE: Budget Proposal for Q3 Today Question on your budget proposal Last week 2016 budget proposal 2 years ago RE: Budget Proposal for Q3 Yesterday
  • 43. Sort by what’s important. Maybe the latest? Subject Sent RE: RE: Budget Proposal for Q3 Today RE: RE: RE: RE: Budget Proposal for Q3 Today RE: Budget Proposal for Q3 Yesterday Question on your budget proposal Last week 2016 budget proposal 2 years ago ↓
  • 44. Then grab all you need. (Voice-first often needs just one result.) Subject Sent RE: RE: Budget Proposal for Q3 Today RE: RE: RE: RE: Budget Proposal for Q3 Today RE: Budget Proposal for Q3 Yesterday Question on your budget proposal Last week 2016 budget proposal 2 years ago ↓
  • 45. Train the User to Reduce the Haystack Understand What’s Best Understood Some terms are better understood by speech to text than others. “Turn off (on?) the lights” “Turn out the lights” You’ll discover this in your testing and in your analytics. People Respond In-Kind People will respond with the same vocabulary as their conversation partners. Be consistent in the output to guide users to the more understandable word choices.
  • 46. But What If There Is No Perfect Result?
  • 47. No Good Results? Do You Really Want to Show Results? Sometimes, asking for clarification is better than showing a best guess. Sometimes, show a best guess is better than asking for clarification. Different Answer for Different Use Cases Different use cases have a different level of tolerance for best guess “How easy is it to back out of this choice?” “Will any damage be done?” Different Media, Different Choices The input and output influence the decision, too.
  • 50. Voice-Added and Voice-First VOICE-ADDED Aides the user in achieving a goal on-screen; the user can always fall back to the screen when voice is unsuited to the task. Can better handle “close” matches.
  • 51. Voice-Added and Voice-First VOICE-FIRST Voice is the primary (or only) input and output mechanism. Less precision than with a display and keyboard input.
  • 52. Voice-Added and Voice-First VOICE-FIRST Return just the right information. The right information for that customer, for that time, for that query. Easily allow customer to make corrections.
  • 53. “Find me this week’s emails about the latest proposal from my team.” sent_before:now sent_after:Sunday team_id:9 Mark every word that’s left optional Sort by number of matching words type:email budget spending
  • 54. Natural Language Queries Better Analytics Optional Words Remove Stop Words Faceting Ignore Plurals Personalization Recent Context Interaction Insights Context Usage Relevance
  • 56. Takeaways Levenshtein Distance Yes; Phonetic Algorithms No Levenshtein distance is a low-cost way to improve relevance Synonyms to handle variety or misunderstandings further improve results Reduce the Haystack Use filters within the spoken query, plus personalization and context Decide If This Calls For a Result Voice-added experiences are more tolerant of approximate results Voice-first and voice-only call for user confirmation and clarification

Editor's Notes

  1. This can apply to all search engines, like Elasticsearch or SOLR, not just Algolia
  2. This can apply to all search engines, like Elasticsearch or SOLR, not just Algolia
  3. Records Attribute Index Queries Relevancy
  4. Records Attribute Index Queries Relevancy
  5. This can apply to all search engines, like Elasticsearch or SOLR, not just Algolia
  6. Let’s examine a sample voice query
  7. Let’s examine a sample voice query
  8. Less precision on voice first, the use case has to match it