SlideShare ist ein Scribd-Unternehmen logo
1 von 19
Downloaden Sie, um offline zu lesen
#SMX #22A @UpasnaGautam
Optimizing for Voice Search & Virtual Assistants
Sound, Search,
and Semantics:
How Form Follows Function
#SMX #22A @UpasnaGautam
▪ Name: Upasna Gautam
▪ Nickname: Pas
▪ Job: SEO Manager at Ziff Davis for
PC Magazine & Mashable
▪ Past Life Job: Scientist/Lab Rat
▪ Other Job: Fitness & Dance Instructor
▪ Hobbies: The Office & hiking
▪ Location: Austin but Michigan is home
About Me
#SMX #22A @UpasnaGautam
Anthony Verre
Veteran SEO & SMX Speaker
Former Boss at Rockfish
Former/Current Mentor
Everyone Tweet at @TonyVerre
and tell him we miss him here!
Shout Out!
#SMX #22A @UpasnaGautam
▪ Automatic Speech Recognition
▪ Sound Processing
▪ Speech Modeling
▪ Quality Metrics
▪ Word Error Rate (WER)
▪ Semantic Quality (Webscore)
▪ Perplexity (PPL)
▪ Out-of-Vocabulary Rate (OOV)
▪ Latency
Agenda
#SMX #22A @UpasnaGautam
▪ The form of a structure is
correlated to the purpose/function
of that structure
▪ When we understand FORM, we
can better understand FUNCTION
Form Follows Function:
Why Is This So Important?
Why don’t you explain this
to me like I’m 5?
#SMX #22A @UpasnaGautam
▪ Before we strategize and implement, we should understand
HOW the voice search system works.
▪ Automatic Speech Recognition (ASR), fueled by deep learning
neural networking, is the system that powers applications like
speech transcription and voice search.
ASR is the FORM behind the voice search FUNCTION
Form Follows Function:
How Does This Apply To Voice Search?
#SMX #22A @UpasnaGautam
Automatic Speech Recognition:
How Do Humans Do It?
Human articulation produces sound waves which
the ear conveys to the brain for processing.
New phone who dis?
#SMX #22A @UpasnaGautam
Automatic Speech Recognition:
How Do Machines Do It?
Part 1: Fourier Transform (Sound Signal Processing)
• Turning sound into math functions that are digested into data
• Extract the most significant coefficients
Part 2: Hidden Markov Model (Speech Modeling)
• Take the newly created sound /math functions and build sequence
of states
• In this model, the states are the letters of the message and the
sequence of events are the sound signal
Part 3:Viterbi Algorithm
• Obtain the sequence of states of maximum likelihood.This “states
of maximum likelihood” are what we get served in the Google
SERPs after submitting a voice search query.
#SMX #22A @UpasnaGautam
Automatic Speech Recognition:
Sound Signal Processing + Speech Modeling
• Convert speech signal into a
sequence of vectors
• Vectors are measured
throughout the duration of the
speech signal
• Using a syntactic decoder, a
valid sequence of
representations is generated
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics
Google has defined and uses a set of metrics to track
the quality of its voice search system.
They use these metrics to drive their research directions
as well as provide insight and guidance for solving
specific problems and tuning system performance.
“We strive to find metrics that illuminate the end-user experience, to make sure that we
optimize the most important aspects and make effective tradeoffs.We also design
metrics which can bring to light specific issues with the underlying technology.” -GOOG
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics
• Word Error Rate (WER)
• SemanticQuality (Webscore)
• Perplexity (PPL)
• Out-of-Vocabulary Rate (OOV)
• Latency
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics:
Word Error Rate (WER)
• Measures misrecognitions at the word level
• Compares the words outputted by the recognizer to those the user really spoke
• Every error (substitution, insertion or deletion) is counted against the recognizer
WER = Number of Substitution + Insertions + Deletions
Total Number ofWords
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics:
Semantic Quality (Webscore)
• Individual word errors do not necessarily effect the final search results shown (deleting
function words like ”in” or ”of,” or minor misspellings, like forgetting an “s” to pluralize)
• The semantic quality of the recognizer (Webscore) is tracked by measuring how many
times the search result as queried by the recognition hypothesis varies from the search
result as queried by a human transcription
• A better recognizer has a higher Webscore
• PageRank + Degree + Betweenness + Closeness
• TheWebscore gives us a much clearer picture of what the user experiences when they
search by voice. Google focuses on optimizing this metric, rather than the more
traditional WER metric defined in the previous slide.
Webscore = Number of Correct Search Results + Deletions
Total Number of Spoken Queries
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics:
Perplexity (PPL)
• Measure of the size of the set of words that can be recognized next, given the previously
recognized words in the query
• Provides a rough measure of the quality of the language model
• The lower the perplexity, the better the model is at predicting the next word
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics:
Out-of-Vocabulary Rate (OOV)
• Tracks the percentage of words spoken by the user that
are not modeled by the language model
• It is important to keep this number as low as possible
• Any word spoken by our users that is not in our
vocabulary will ultimately result in a recognition error
• Recognition errors may also cause errors in surrounding
words due to the subsequent poor predictions of the
language model and acoustic misalignments
#SMX #22A @UpasnaGautam
Google’s Voice Search Quality Metrics:
Latency
Contributing Factors
• Time it takes the system to detect end-of-speech
• Total time to recognize the spoken query
• Time to perform the web query
• Time to return the web search results back to the
client over the network
• Time it takes to render the search results in the
browser of the users phone.
The total time (in seconds) it takes to complete a search by voice. More specifically, the
time from when the user finishes speaking until the search results appear on screen
Each of these factors are studied and optimized to provide a streamlined user experience.
#SMX #22A @UpasnaGautam
Share these #SMXInsights on your social channels!
#SMXInsights
▪ To Understand Automatic Speech
Recognition is to Understand Voice Search
▪ ASR is the form behind the voice
search function
▪ Sound processing and speech modeling
power voice search results
#SMX #22A @UpasnaGautam
Share these #SMXInsights on your social channels!
#SMXInsights
▪ Semantic Quality is EVERYTHING.
▪ Keyword research must include user behavior
research & consumer journey analyses to
uncover natural language patterns
▪ Google’s recognition hypotheses and human
transcription are in sync – we need to serve the
resources (aka content) that facilitate that sync
▪ Long-Tail is Life
#SMX #22A @UpasnaGautam
Share these #SMXInsights on your social channels!
#SMXInsights
▪ A High-Quality UX is a Fast UX
▪ From the time it takes to detect end-of-speech,
to the time it takes to render the search results,
time is of the essence during speech processing.
▪ “It is generally desirable to reduce any user noticeable latency, and
in certain circumstances may be desirable to reduce latency even if
improved speed comes at the cost of reduced quality ASR results.”
-GOOG

Weitere ähnliche Inhalte

Ähnlich wie Sound, Search, and Semantics: How Form Follows Function

Relevancy and Search Quality Analysis - Search Technologies
Relevancy and Search Quality Analysis - Search TechnologiesRelevancy and Search Quality Analysis - Search Technologies
Relevancy and Search Quality Analysis - Search Technologies
enterprisesearchmeetup
 
2016-08-22_winning_on_technicalities_for_linkedin
2016-08-22_winning_on_technicalities_for_linkedin2016-08-22_winning_on_technicalities_for_linkedin
2016-08-22_winning_on_technicalities_for_linkedin
Daniel Thornton
 
Inside, Outside Research Brochure
Inside, Outside Research BrochureInside, Outside Research Brochure
Inside, Outside Research Brochure
jones_kristen
 

Ähnlich wie Sound, Search, and Semantics: How Form Follows Function (20)

Alexa, How Do I Do SEO For You? By Navneet Virk
Alexa, How Do I Do SEO For You? By Navneet VirkAlexa, How Do I Do SEO For You? By Navneet Virk
Alexa, How Do I Do SEO For You? By Navneet Virk
 
Relevancy and Search Quality Analysis - Search Technologies
Relevancy and Search Quality Analysis - Search TechnologiesRelevancy and Search Quality Analysis - Search Technologies
Relevancy and Search Quality Analysis - Search Technologies
 
How Google works
How Google worksHow Google works
How Google works
 
Semantics and Search by Upasna Gautam at PubCon Austin 2018
Semantics and Search by Upasna Gautam at PubCon Austin 2018Semantics and Search by Upasna Gautam at PubCon Austin 2018
Semantics and Search by Upasna Gautam at PubCon Austin 2018
 
Build your "Skills": Getting your Content Ready for Voice and Chatbots
Build your "Skills": Getting your Content Ready for Voice and ChatbotsBuild your "Skills": Getting your Content Ready for Voice and Chatbots
Build your "Skills": Getting your Content Ready for Voice and Chatbots
 
AI, Search, and the Disruption of Knowledge Management
AI, Search, and the Disruption of Knowledge ManagementAI, Search, and the Disruption of Knowledge Management
AI, Search, and the Disruption of Knowledge Management
 
Tools of the Trade for Running SEO Audits - SMX East 2015: Essential Steps fo...
Tools of the Trade for Running SEO Audits - SMX East 2015: Essential Steps fo...Tools of the Trade for Running SEO Audits - SMX East 2015: Essential Steps fo...
Tools of the Trade for Running SEO Audits - SMX East 2015: Essential Steps fo...
 
How to Uncover Big Growth Opportunities with Data
How to Uncover Big Growth Opportunities with DataHow to Uncover Big Growth Opportunities with Data
How to Uncover Big Growth Opportunities with Data
 
Digital marketing
Digital marketingDigital marketing
Digital marketing
 
Diagnosing and fixing drop in rankings - SMXnext2020
Diagnosing and fixing drop in rankings - SMXnext2020Diagnosing and fixing drop in rankings - SMXnext2020
Diagnosing and fixing drop in rankings - SMXnext2020
 
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai searchChatGPT-and-Generative-AI-Landscape Working of generative ai search
ChatGPT-and-Generative-AI-Landscape Working of generative ai search
 
T44u 2015, web development best practice
T44u 2015, web development best practiceT44u 2015, web development best practice
T44u 2015, web development best practice
 
A Tale of Two Case Studies: Using LLMs in Production
A Tale of Two Case Studies: Using LLMs in ProductionA Tale of Two Case Studies: Using LLMs in Production
A Tale of Two Case Studies: Using LLMs in Production
 
SEO Audit Tools, Tips and Tricks - SMX West 2016
SEO Audit Tools, Tips and Tricks - SMX West 2016SEO Audit Tools, Tips and Tricks - SMX West 2016
SEO Audit Tools, Tips and Tricks - SMX West 2016
 
2016-08-22_winning_on_technicalities_for_linkedin
2016-08-22_winning_on_technicalities_for_linkedin2016-08-22_winning_on_technicalities_for_linkedin
2016-08-22_winning_on_technicalities_for_linkedin
 
Nondeterministic Software for the Rest of Us
Nondeterministic Software for the Rest of UsNondeterministic Software for the Rest of Us
Nondeterministic Software for the Rest of Us
 
SEO - What is it?
SEO - What is it?SEO - What is it?
SEO - What is it?
 
Inside, Outside Research Brochure
Inside, Outside Research BrochureInside, Outside Research Brochure
Inside, Outside Research Brochure
 
Winning Keyword Research Strategies for 2018
Winning Keyword ResearchStrategies for 2018Winning Keyword ResearchStrategies for 2018
Winning Keyword Research Strategies for 2018
 
Enhancing Enterprise Search with Machine Learning - Simon Hughes, Dice.com
Enhancing Enterprise Search with Machine Learning - Simon Hughes, Dice.comEnhancing Enterprise Search with Machine Learning - Simon Hughes, Dice.com
Enhancing Enterprise Search with Machine Learning - Simon Hughes, Dice.com
 

Kürzlich hochgeladen

一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制
一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制
一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制
pxcywzqs
 
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
ayvbos
 
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理
F
 
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girlsRussian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Monica Sydney
 
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsIndian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Monica Sydney
 
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu DhabiAbu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Monica Sydney
 
一比一原版田纳西大学毕业证如何办理
一比一原版田纳西大学毕业证如何办理一比一原版田纳西大学毕业证如何办理
一比一原版田纳西大学毕业证如何办理
F
 
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
ydyuyu
 
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
ydyuyu
 
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
ydyuyu
 

Kürzlich hochgeladen (20)

一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制
一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制
一比一原版(Offer)康考迪亚大学毕业证学位证靠谱定制
 
Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.
 
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
 
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
 
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
call girls in Anand Vihar (delhi) call me [🔝9953056974🔝] escort service 24X7
 
Call girls Service in Ajman 0505086370 Ajman call girls
Call girls Service in Ajman 0505086370 Ajman call girlsCall girls Service in Ajman 0505086370 Ajman call girls
Call girls Service in Ajman 0505086370 Ajman call girls
 
20240507 QFM013 Machine Intelligence Reading List April 2024.pdf
20240507 QFM013 Machine Intelligence Reading List April 2024.pdf20240507 QFM013 Machine Intelligence Reading List April 2024.pdf
20240507 QFM013 Machine Intelligence Reading List April 2024.pdf
 
一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理一比一原版奥兹学院毕业证如何办理
一比一原版奥兹学院毕业证如何办理
 
Story Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
Story Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrStory Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
Story Board.pptxrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
 
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girlsRussian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
Russian Call girls in Abu Dhabi 0508644382 Abu Dhabi Call girls
 
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
 
Real Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtReal Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirt
 
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsIndian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
 
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu DhabiAbu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
Abu Dhabi Escorts Service 0508644382 Escorts in Abu Dhabi
 
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
 
一比一原版田纳西大学毕业证如何办理
一比一原版田纳西大学毕业证如何办理一比一原版田纳西大学毕业证如何办理
一比一原版田纳西大学毕业证如何办理
 
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
 
APNIC Updates presented by Paul Wilson at ARIN 53
APNIC Updates presented by Paul Wilson at ARIN 53APNIC Updates presented by Paul Wilson at ARIN 53
APNIC Updates presented by Paul Wilson at ARIN 53
 
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
 
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
 

Sound, Search, and Semantics: How Form Follows Function

  • 1. #SMX #22A @UpasnaGautam Optimizing for Voice Search & Virtual Assistants Sound, Search, and Semantics: How Form Follows Function
  • 2. #SMX #22A @UpasnaGautam ▪ Name: Upasna Gautam ▪ Nickname: Pas ▪ Job: SEO Manager at Ziff Davis for PC Magazine & Mashable ▪ Past Life Job: Scientist/Lab Rat ▪ Other Job: Fitness & Dance Instructor ▪ Hobbies: The Office & hiking ▪ Location: Austin but Michigan is home About Me
  • 3. #SMX #22A @UpasnaGautam Anthony Verre Veteran SEO & SMX Speaker Former Boss at Rockfish Former/Current Mentor Everyone Tweet at @TonyVerre and tell him we miss him here! Shout Out!
  • 4. #SMX #22A @UpasnaGautam ▪ Automatic Speech Recognition ▪ Sound Processing ▪ Speech Modeling ▪ Quality Metrics ▪ Word Error Rate (WER) ▪ Semantic Quality (Webscore) ▪ Perplexity (PPL) ▪ Out-of-Vocabulary Rate (OOV) ▪ Latency Agenda
  • 5. #SMX #22A @UpasnaGautam ▪ The form of a structure is correlated to the purpose/function of that structure ▪ When we understand FORM, we can better understand FUNCTION Form Follows Function: Why Is This So Important? Why don’t you explain this to me like I’m 5?
  • 6. #SMX #22A @UpasnaGautam ▪ Before we strategize and implement, we should understand HOW the voice search system works. ▪ Automatic Speech Recognition (ASR), fueled by deep learning neural networking, is the system that powers applications like speech transcription and voice search. ASR is the FORM behind the voice search FUNCTION Form Follows Function: How Does This Apply To Voice Search?
  • 7. #SMX #22A @UpasnaGautam Automatic Speech Recognition: How Do Humans Do It? Human articulation produces sound waves which the ear conveys to the brain for processing. New phone who dis?
  • 8. #SMX #22A @UpasnaGautam Automatic Speech Recognition: How Do Machines Do It? Part 1: Fourier Transform (Sound Signal Processing) • Turning sound into math functions that are digested into data • Extract the most significant coefficients Part 2: Hidden Markov Model (Speech Modeling) • Take the newly created sound /math functions and build sequence of states • In this model, the states are the letters of the message and the sequence of events are the sound signal Part 3:Viterbi Algorithm • Obtain the sequence of states of maximum likelihood.This “states of maximum likelihood” are what we get served in the Google SERPs after submitting a voice search query.
  • 9. #SMX #22A @UpasnaGautam Automatic Speech Recognition: Sound Signal Processing + Speech Modeling • Convert speech signal into a sequence of vectors • Vectors are measured throughout the duration of the speech signal • Using a syntactic decoder, a valid sequence of representations is generated
  • 10. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics Google has defined and uses a set of metrics to track the quality of its voice search system. They use these metrics to drive their research directions as well as provide insight and guidance for solving specific problems and tuning system performance. “We strive to find metrics that illuminate the end-user experience, to make sure that we optimize the most important aspects and make effective tradeoffs.We also design metrics which can bring to light specific issues with the underlying technology.” -GOOG
  • 11. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics • Word Error Rate (WER) • SemanticQuality (Webscore) • Perplexity (PPL) • Out-of-Vocabulary Rate (OOV) • Latency
  • 12. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics: Word Error Rate (WER) • Measures misrecognitions at the word level • Compares the words outputted by the recognizer to those the user really spoke • Every error (substitution, insertion or deletion) is counted against the recognizer WER = Number of Substitution + Insertions + Deletions Total Number ofWords
  • 13. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics: Semantic Quality (Webscore) • Individual word errors do not necessarily effect the final search results shown (deleting function words like ”in” or ”of,” or minor misspellings, like forgetting an “s” to pluralize) • The semantic quality of the recognizer (Webscore) is tracked by measuring how many times the search result as queried by the recognition hypothesis varies from the search result as queried by a human transcription • A better recognizer has a higher Webscore • PageRank + Degree + Betweenness + Closeness • TheWebscore gives us a much clearer picture of what the user experiences when they search by voice. Google focuses on optimizing this metric, rather than the more traditional WER metric defined in the previous slide. Webscore = Number of Correct Search Results + Deletions Total Number of Spoken Queries
  • 14. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics: Perplexity (PPL) • Measure of the size of the set of words that can be recognized next, given the previously recognized words in the query • Provides a rough measure of the quality of the language model • The lower the perplexity, the better the model is at predicting the next word
  • 15. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics: Out-of-Vocabulary Rate (OOV) • Tracks the percentage of words spoken by the user that are not modeled by the language model • It is important to keep this number as low as possible • Any word spoken by our users that is not in our vocabulary will ultimately result in a recognition error • Recognition errors may also cause errors in surrounding words due to the subsequent poor predictions of the language model and acoustic misalignments
  • 16. #SMX #22A @UpasnaGautam Google’s Voice Search Quality Metrics: Latency Contributing Factors • Time it takes the system to detect end-of-speech • Total time to recognize the spoken query • Time to perform the web query • Time to return the web search results back to the client over the network • Time it takes to render the search results in the browser of the users phone. The total time (in seconds) it takes to complete a search by voice. More specifically, the time from when the user finishes speaking until the search results appear on screen Each of these factors are studied and optimized to provide a streamlined user experience.
  • 17. #SMX #22A @UpasnaGautam Share these #SMXInsights on your social channels! #SMXInsights ▪ To Understand Automatic Speech Recognition is to Understand Voice Search ▪ ASR is the form behind the voice search function ▪ Sound processing and speech modeling power voice search results
  • 18. #SMX #22A @UpasnaGautam Share these #SMXInsights on your social channels! #SMXInsights ▪ Semantic Quality is EVERYTHING. ▪ Keyword research must include user behavior research & consumer journey analyses to uncover natural language patterns ▪ Google’s recognition hypotheses and human transcription are in sync – we need to serve the resources (aka content) that facilitate that sync ▪ Long-Tail is Life
  • 19. #SMX #22A @UpasnaGautam Share these #SMXInsights on your social channels! #SMXInsights ▪ A High-Quality UX is a Fast UX ▪ From the time it takes to detect end-of-speech, to the time it takes to render the search results, time is of the essence during speech processing. ▪ “It is generally desirable to reduce any user noticeable latency, and in certain circumstances may be desirable to reduce latency even if improved speed comes at the cost of reduced quality ASR results.” -GOOG