SlideShare a Scribd company logo
Using Asterisk 
to create “Her”
CAN YOU SPEAK MAGIC? 
2 
Allison Smith Ben Klang 
as “Her”
CAN YOU SPEAK MAGIC? 
3
CAN YOU SPEAK MAGIC? 
3
CAN YOU SPEAK MAGIC? 
ALL ABOUT “HER” 
4 
Allison
CAN YOU SPEAK MAGIC? 
5
CAN YOU SPEAK MAGIC? 
HOW DOES THIS WORK IN ASTERISK 
•We have access to the same core tech 
•ASR: Automatic Speech Recognition 
•NLU: Natural Language Understanding 
•TTS: Text-to-Speech 
•API: Application Program Interfaces 
•But it’s not just about the tech 
•It has to be useful 
•It has to usable 
6
CAN YOU SPEAK MAGIC? 
USABILITY: “HER” PERSONALITY 
7
CAN YOU SPEAK MAGIC? 
CREATING “HER” PERSONALITY 
•What kind of assistant is she? 
•Straight, no-nonsense 
•Bubbly, friendly 
•Sassy, smart-mouthed 
•Relaxed, laid back 
•Energetic, excited 
•Sultry, provocative 
8
CAN YOU SPEAK MAGIC? 
WHY PERSONALITY MATTERS 
9
CAN YOU SPEAK MAGIC? 
HOW DOES “SHE” WORK? 
10
CAN YOU SPEAK MAGIC? 
INSIDE “HER” 
ASR Recognizing 
Researching API NLU Understanding 
11 
Responding TTS 
Input/Output Channel 
Voice
CAN YOU SPEAK MAGIC? 
INSIDE “HER” 
ASR Recognizing 
Researching API NLU Understanding 
12 
Responding TTS 
Input/Output Channel 
Voice
CAN YOU SPEAK MAGIC? 
RECOGNIZING 
•Different kinds of ASR 
•Dictation / Transcription 
•Grammar-based 
•Hotword 
•Biometrics / Identity 
•DTMF has its place 
•The Media Connection 
•MRCP 
•HTTP APIs 
13
CAN YOU SPEAK MAGIC? 
RECOGNIZING INTERFACES 
•MRCP 
+ Streaming recognition = fastest response 
+ MRCPv2 is SIP-based 
– Somewhat more complex 
– Mobile-app unfriendly 
•HTTP API 
+ Mobile-friendly 
+ Simple API 
– Record-and-upload = slower response 
14
CAN YOU SPEAK MAGIC? 
15 
ASR 
Vendors 
/ 
MRCP HTTP Grammar Dictation Hotword 
Nuance ✓ ✓ ✓ ✓ ✓ 
Lumenvox ✓ ✓ 
Vestec ✓ ✓ ✓ 
AT&T 
Watson ✓ ✓ ✓ 
Google ✓ ✓
CAN YOU SPEAK MAGIC? 
INSIDE “HER” 
ASR Recognizing 
Researching API NLU Understanding 
16 
Responding TTS 
Input/Output Channel 
Voice
CAN YOU SPEAK MAGIC? 
GRAMMAR-BASED RECOG 
17 
Where would you like to go? 
Chicago 
Tell me the month and day you want to leave? 
August fifth 
Tell me the month and day you want to return? 
August eighth 
What can I help you with? 
Book a flight 
Where are you flying from? 
Atlanta
CAN YOU SPEAK MAGIC? 
NATURAL LANGUAGE 
“Hm, I want to go to AstriCon in Las Vegas on 
October 21st for three days, and I want the last flight out.” 
✓ Destination 
✓ Departing Date 
✓ Returning Date 
+ Extra Constraint 
18 
? Origin
CAN YOU SPEAK MAGIC? 
INSIDE “HER” 
ASR Recognizing 
Researching API NLU Understanding 
19 
Responding TTS 
Input/Output Channel 
Voice
CAN YOU SPEAK MAGIC? 
20 
Send a tweet… Check in at… 
What is the weather today? 
Get me a table for two… 
Who won the game last night? 
What is Google 
trading at? 
When is my 
next appointment?
CAN YOU SPEAK MAGIC? 
ZZZZZZzzzzzz…… 
20 
Send a tweet… Check in at… 
What is the weather today? 
Get me a table for two… 
Who won the game last night? 
What is Google 
trading at? 
When is my 
next appointment?
CAN YOU SPEAK MAGIC? 
21 
How much have we sold 
so far this month? 
How many sales reps 
are still in homes? 
How many callers 
are in the queue 
right now? 
Add my manager to this call 
When is my next open 
appointment slot?
CAN YOU SPEAK MAGIC? 
INSIDE “HER” 
ASR Recognizing 
Researching API NLU Understanding 
22 
Responding TTS 
Input/Output Channel 
Voice
CAN YOU SPEAK MAGIC? 
TEXT-TO-SPEECH 
•Choose your voice carefully 
•Voice DBs’ quality varies widely 
•Tone of voice imparts as much as content 
•Mix TTS with recorded audio 
•Consider context of user 
•Check prosody (rate, pitch, volume) 
•Structure answers similarly to questions 
•Give option to repeat 
•Speech Synthesis Markup 
23
CAN YOU SPEAK MAGIC? 
INSIDE “HER” 
ASR Recognizing 
Researching API NLU Understanding 
24 
Responding TTS 
Input/Output Channel 
Voice
CAN YOU SPEAK MAGIC? 
BEYOND VOICE: 
GETTING VISUAL 
25
CAN YOU SPEAK MAGIC? 
MULTI-MODE APPS 
•Request information by voice 
•Receive information via screen 
•SMS 
•Web browser (WebRTC!) 
•Allow continued input from alternate 
source 
•Respond via mouse click *or* voice 
26
CAN YOU SPEAK MAGIC? 
27
CAN YOU SPEAK MAGIC? 
QUESTIONS? 
PS: ALLISON WANTS TO BE THE 
NEXT SIRI! 
28

More Related Content

Viewers also liked

MATLAB Examen - Enero
MATLAB Examen - EneroMATLAB Examen - Enero
MATLAB Examen - Enero
Jose Cordova
 
Practica 2 - VOIP II
Practica 2 - VOIP IIPractica 2 - VOIP II
Practica 2 - VOIP II
Jose Cordova
 
Practica 8
Practica 8Practica 8
Practica 8
Jose Cordova
 
MATLAB Febrero - Practica 3
MATLAB Febrero - Practica 3MATLAB Febrero - Practica 3
MATLAB Febrero - Practica 3
Jose Cordova
 
Practica 5
Practica 5Practica 5
Practica 5
Jose Cordova
 
MATLAB Febrero - Practica 4
MATLAB Febrero - Practica 4MATLAB Febrero - Practica 4
MATLAB Febrero - Practica 4
Jose Cordova
 
Practica 6
Practica 6Practica 6
Practica 6
Jose Cordova
 
Practica 4
Practica 4Practica 4
Practica 4
Jose Cordova
 
MATLAB Febrero - Practica 2
MATLAB Febrero - Practica 2MATLAB Febrero - Practica 2
MATLAB Febrero - Practica 2
Jose Cordova
 
MATLAB Marzo - Examen
MATLAB Marzo - ExamenMATLAB Marzo - Examen
MATLAB Marzo - Examen
Jose Cordova
 
Astricon 2013: "Asterisk and Database"
Astricon 2013: "Asterisk and Database"Astricon 2013: "Asterisk and Database"
Astricon 2013: "Asterisk and Database"
Francesco Prior
 
MATLAB Examen Junio 2010
MATLAB Examen Junio 2010MATLAB Examen Junio 2010
MATLAB Examen Junio 2010
Jose Cordova
 
Home Automation with Asterisk - Astricon 2015 - Alberto Sagredo Castro
Home Automation with Asterisk - Astricon 2015 - Alberto Sagredo CastroHome Automation with Asterisk - Astricon 2015 - Alberto Sagredo Castro
Home Automation with Asterisk - Astricon 2015 - Alberto Sagredo Castro
Alberto Sagredo Castro
 
Tecnicas monitoreo reportes con Asterisk
Tecnicas monitoreo reportes con AsteriskTecnicas monitoreo reportes con Asterisk
Tecnicas monitoreo reportes con Asterisk
Nicolás Gudiño
 
Asterisk, HTML5 and NodeJS; a world of endless possibilities
Asterisk, HTML5 and NodeJS; a world of endless possibilitiesAsterisk, HTML5 and NodeJS; a world of endless possibilities
Asterisk, HTML5 and NodeJS; a world of endless possibilities
Dan Jenkins
 
Visual Design with Data
Visual Design with DataVisual Design with Data
Visual Design with Data
Seth Familian
 

Viewers also liked (16)

MATLAB Examen - Enero
MATLAB Examen - EneroMATLAB Examen - Enero
MATLAB Examen - Enero
 
Practica 2 - VOIP II
Practica 2 - VOIP IIPractica 2 - VOIP II
Practica 2 - VOIP II
 
Practica 8
Practica 8Practica 8
Practica 8
 
MATLAB Febrero - Practica 3
MATLAB Febrero - Practica 3MATLAB Febrero - Practica 3
MATLAB Febrero - Practica 3
 
Practica 5
Practica 5Practica 5
Practica 5
 
MATLAB Febrero - Practica 4
MATLAB Febrero - Practica 4MATLAB Febrero - Practica 4
MATLAB Febrero - Practica 4
 
Practica 6
Practica 6Practica 6
Practica 6
 
Practica 4
Practica 4Practica 4
Practica 4
 
MATLAB Febrero - Practica 2
MATLAB Febrero - Practica 2MATLAB Febrero - Practica 2
MATLAB Febrero - Practica 2
 
MATLAB Marzo - Examen
MATLAB Marzo - ExamenMATLAB Marzo - Examen
MATLAB Marzo - Examen
 
Astricon 2013: "Asterisk and Database"
Astricon 2013: "Asterisk and Database"Astricon 2013: "Asterisk and Database"
Astricon 2013: "Asterisk and Database"
 
MATLAB Examen Junio 2010
MATLAB Examen Junio 2010MATLAB Examen Junio 2010
MATLAB Examen Junio 2010
 
Home Automation with Asterisk - Astricon 2015 - Alberto Sagredo Castro
Home Automation with Asterisk - Astricon 2015 - Alberto Sagredo CastroHome Automation with Asterisk - Astricon 2015 - Alberto Sagredo Castro
Home Automation with Asterisk - Astricon 2015 - Alberto Sagredo Castro
 
Tecnicas monitoreo reportes con Asterisk
Tecnicas monitoreo reportes con AsteriskTecnicas monitoreo reportes con Asterisk
Tecnicas monitoreo reportes con Asterisk
 
Asterisk, HTML5 and NodeJS; a world of endless possibilities
Asterisk, HTML5 and NodeJS; a world of endless possibilitiesAsterisk, HTML5 and NodeJS; a world of endless possibilities
Asterisk, HTML5 and NodeJS; a world of endless possibilities
 
Visual Design with Data
Visual Design with DataVisual Design with Data
Visual Design with Data
 

Similar to Using Asterisk to Create "Her"

Semantic vs. Statistic Language Model Expansion
Semantic vs. Statistic Language Model ExpansionSemantic vs. Statistic Language Model Expansion
Semantic vs. Statistic Language Model Expansion
Yuval Krymolowski
 
Alexa, say hi! Intro to Alexa for developers
Alexa, say hi! Intro to  Alexa for developersAlexa, say hi! Intro to  Alexa for developers
Alexa, say hi! Intro to Alexa for developers
Katarzyna Kurzyńska
 
Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...
Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...
Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...
Christophe Willemsen
 
An Introduction to Amazon AI
An Introduction to Amazon AIAn Introduction to Amazon AI
An Introduction to Amazon AI
Amazon Web Services
 
Building an AI-based service with Rekognition, Polly and Lex
Building an AI-based service with Rekognition, Polly and LexBuilding an AI-based service with Rekognition, Polly and Lex
Building an AI-based service with Rekognition, Polly and Lex
Amazon Web Services
 
Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017
Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017
Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017
Amazon Web Services
 
ALX326_Applying Alexa’s Natural Language to Your Challenges
ALX326_Applying Alexa’s Natural Language to Your ChallengesALX326_Applying Alexa’s Natural Language to Your Challenges
ALX326_Applying Alexa’s Natural Language to Your Challenges
Amazon Web Services
 
Little words of wisdom for the developer - Guillaume Laforge (Pivotal)
Little words of wisdom for the developer - Guillaume Laforge (Pivotal)Little words of wisdom for the developer - Guillaume Laforge (Pivotal)
Little words of wisdom for the developer - Guillaume Laforge (Pivotal)
jaxLondonConference
 
LSS2017: Voice Search...It's the Wave of Today
LSS2017: Voice Search...It's the Wave of TodayLSS2017: Voice Search...It's the Wave of Today
LSS2017: Voice Search...It's the Wave of Today
Rio SEO
 
AI in industry
AI in industryAI in industry
AI in industry
Anurag Bhandari
 
More Than Words: Localizing Your International Content
More Than Words: Localizing Your International ContentMore Than Words: Localizing Your International Content
More Than Words: Localizing Your International Content
Zeph Snapp
 
How to Augment your Marketing Strategy with Alexa - August 22, 2019
How to Augment your Marketing Strategy with Alexa - August 22, 2019How to Augment your Marketing Strategy with Alexa - August 22, 2019
How to Augment your Marketing Strategy with Alexa - August 22, 2019
Caroline Dunn
 
Short URLs, Big Fun
Short URLs, Big FunShort URLs, Big Fun
Short URLs, Big Fun
Hilary Mason
 
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Codemotion
 
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Codemotion
 
Dealing with a search engine in your application - a Solr approach for beginners
Dealing with a search engine in your application - a Solr approach for beginnersDealing with a search engine in your application - a Solr approach for beginners
Dealing with a search engine in your application - a Solr approach for beginners
Elaine Naomi
 
UX STRAT Europe 2019: Zhaochang He, VMware
UX STRAT Europe 2019: Zhaochang He, VMwareUX STRAT Europe 2019: Zhaochang He, VMware
UX STRAT Europe 2019: Zhaochang He, VMware
UX STRAT
 

Similar to Using Asterisk to Create "Her" (17)

Semantic vs. Statistic Language Model Expansion
Semantic vs. Statistic Language Model ExpansionSemantic vs. Statistic Language Model Expansion
Semantic vs. Statistic Language Model Expansion
 
Alexa, say hi! Intro to Alexa for developers
Alexa, say hi! Intro to  Alexa for developersAlexa, say hi! Intro to  Alexa for developers
Alexa, say hi! Intro to Alexa for developers
 
Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...
Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...
Chatbots and Voice Conversational Interfaces with Amazon Alexa, Neo4j and Gra...
 
An Introduction to Amazon AI
An Introduction to Amazon AIAn Introduction to Amazon AI
An Introduction to Amazon AI
 
Building an AI-based service with Rekognition, Polly and Lex
Building an AI-based service with Rekognition, Polly and LexBuilding an AI-based service with Rekognition, Polly and Lex
Building an AI-based service with Rekognition, Polly and Lex
 
Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017
Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017
Applying Alexa’s Natural Language to Your Challenges - ALX326 - re:Invent 2017
 
ALX326_Applying Alexa’s Natural Language to Your Challenges
ALX326_Applying Alexa’s Natural Language to Your ChallengesALX326_Applying Alexa’s Natural Language to Your Challenges
ALX326_Applying Alexa’s Natural Language to Your Challenges
 
Little words of wisdom for the developer - Guillaume Laforge (Pivotal)
Little words of wisdom for the developer - Guillaume Laforge (Pivotal)Little words of wisdom for the developer - Guillaume Laforge (Pivotal)
Little words of wisdom for the developer - Guillaume Laforge (Pivotal)
 
LSS2017: Voice Search...It's the Wave of Today
LSS2017: Voice Search...It's the Wave of TodayLSS2017: Voice Search...It's the Wave of Today
LSS2017: Voice Search...It's the Wave of Today
 
AI in industry
AI in industryAI in industry
AI in industry
 
More Than Words: Localizing Your International Content
More Than Words: Localizing Your International ContentMore Than Words: Localizing Your International Content
More Than Words: Localizing Your International Content
 
How to Augment your Marketing Strategy with Alexa - August 22, 2019
How to Augment your Marketing Strategy with Alexa - August 22, 2019How to Augment your Marketing Strategy with Alexa - August 22, 2019
How to Augment your Marketing Strategy with Alexa - August 22, 2019
 
Short URLs, Big Fun
Short URLs, Big FunShort URLs, Big Fun
Short URLs, Big Fun
 
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
 
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
Mark Bate - Building Next Level Voice Games with Alexa - Codemotion Berlin 2018
 
Dealing with a search engine in your application - a Solr approach for beginners
Dealing with a search engine in your application - a Solr approach for beginnersDealing with a search engine in your application - a Solr approach for beginners
Dealing with a search engine in your application - a Solr approach for beginners
 
UX STRAT Europe 2019: Zhaochang He, VMware
UX STRAT Europe 2019: Zhaochang He, VMwareUX STRAT Europe 2019: Zhaochang He, VMware
UX STRAT Europe 2019: Zhaochang He, VMware
 

More from Mojo Lingo

ConnectJS 2015: Video Killed the Telephone Star
ConnectJS 2015: Video Killed the Telephone StarConnectJS 2015: Video Killed the Telephone Star
ConnectJS 2015: Video Killed the Telephone Star
Mojo Lingo
 
AstriCon 2015: WebRTC: How it Works, and How it Breaks
AstriCon 2015: WebRTC: How it Works, and How it BreaksAstriCon 2015: WebRTC: How it Works, and How it Breaks
AstriCon 2015: WebRTC: How it Works, and How it Breaks
Mojo Lingo
 
FreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In Sight
FreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In SightFreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In Sight
FreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In Sight
Mojo Lingo
 
Now Hear This! Putting Voice, Video, and Text into Ruby on Rails
Now Hear This! Putting Voice, Video, and Text into Ruby on RailsNow Hear This! Putting Voice, Video, and Text into Ruby on Rails
Now Hear This! Putting Voice, Video, and Text into Ruby on Rails
Mojo Lingo
 
Tipping the Scales: Measuring and Scaling Asterisk
Tipping the Scales: Measuring and Scaling AsteriskTipping the Scales: Measuring and Scaling Asterisk
Tipping the Scales: Measuring and Scaling Asterisk
Mojo Lingo
 
WebRTC Overview by Dan Burnett
WebRTC Overview by Dan BurnettWebRTC Overview by Dan Burnett
WebRTC Overview by Dan Burnett
Mojo Lingo
 
AdhearsionConf 2013 Keynote
AdhearsionConf 2013 KeynoteAdhearsionConf 2013 Keynote
AdhearsionConf 2013 Keynote
Mojo Lingo
 
Speech-Enabling Web Apps
Speech-Enabling Web AppsSpeech-Enabling Web Apps
Speech-Enabling Web Apps
Mojo Lingo
 
WebRTC: What? How? Why? - ClueCon 2013
WebRTC: What? How? Why? - ClueCon 2013WebRTC: What? How? Why? - ClueCon 2013
WebRTC: What? How? Why? - ClueCon 2013
Mojo Lingo
 
Infiltrando Telecoms Usando Ruby
Infiltrando Telecoms Usando RubyInfiltrando Telecoms Usando Ruby
Infiltrando Telecoms Usando Ruby
Mojo Lingo
 
Enhancing FreePBX with Adhearsion
Enhancing FreePBX with AdhearsionEnhancing FreePBX with Adhearsion
Enhancing FreePBX with Adhearsion
Mojo Lingo
 
Connecting Adhearsion
Connecting AdhearsionConnecting Adhearsion
Connecting Adhearsion
Mojo Lingo
 
Testing Adhearsion Applications
Testing Adhearsion ApplicationsTesting Adhearsion Applications
Testing Adhearsion Applications
Mojo Lingo
 
Testing Telephony: It's Not All Terrible
Testing Telephony: It's Not All TerribleTesting Telephony: It's Not All Terrible
Testing Telephony: It's Not All Terrible
Mojo Lingo
 
Rayo for XMPP Folks
Rayo for XMPP FolksRayo for XMPP Folks
Rayo for XMPP Folks
Mojo Lingo
 
Talking To Rails
Talking To RailsTalking To Rails
Talking To Rails
Mojo Lingo
 
Building Real Life Applications with Adhearsion
Building Real Life Applications with AdhearsionBuilding Real Life Applications with Adhearsion
Building Real Life Applications with Adhearsion
Mojo Lingo
 
Keeping It Realtime!
Keeping It Realtime!Keeping It Realtime!
Keeping It Realtime!
Mojo Lingo
 
Integrating Voice Through Adhearsion
Integrating Voice Through AdhearsionIntegrating Voice Through Adhearsion
Integrating Voice Through Adhearsion
Mojo Lingo
 
Infiltrating Telecoms Using Ruby
Infiltrating Telecoms Using RubyInfiltrating Telecoms Using Ruby
Infiltrating Telecoms Using Ruby
Mojo Lingo
 

More from Mojo Lingo (20)

ConnectJS 2015: Video Killed the Telephone Star
ConnectJS 2015: Video Killed the Telephone StarConnectJS 2015: Video Killed the Telephone Star
ConnectJS 2015: Video Killed the Telephone Star
 
AstriCon 2015: WebRTC: How it Works, and How it Breaks
AstriCon 2015: WebRTC: How it Works, and How it BreaksAstriCon 2015: WebRTC: How it Works, and How it Breaks
AstriCon 2015: WebRTC: How it Works, and How it Breaks
 
FreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In Sight
FreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In SightFreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In Sight
FreeSWITCH, FreeSWITCH Everywhere, and Not A Phone In Sight
 
Now Hear This! Putting Voice, Video, and Text into Ruby on Rails
Now Hear This! Putting Voice, Video, and Text into Ruby on RailsNow Hear This! Putting Voice, Video, and Text into Ruby on Rails
Now Hear This! Putting Voice, Video, and Text into Ruby on Rails
 
Tipping the Scales: Measuring and Scaling Asterisk
Tipping the Scales: Measuring and Scaling AsteriskTipping the Scales: Measuring and Scaling Asterisk
Tipping the Scales: Measuring and Scaling Asterisk
 
WebRTC Overview by Dan Burnett
WebRTC Overview by Dan BurnettWebRTC Overview by Dan Burnett
WebRTC Overview by Dan Burnett
 
AdhearsionConf 2013 Keynote
AdhearsionConf 2013 KeynoteAdhearsionConf 2013 Keynote
AdhearsionConf 2013 Keynote
 
Speech-Enabling Web Apps
Speech-Enabling Web AppsSpeech-Enabling Web Apps
Speech-Enabling Web Apps
 
WebRTC: What? How? Why? - ClueCon 2013
WebRTC: What? How? Why? - ClueCon 2013WebRTC: What? How? Why? - ClueCon 2013
WebRTC: What? How? Why? - ClueCon 2013
 
Infiltrando Telecoms Usando Ruby
Infiltrando Telecoms Usando RubyInfiltrando Telecoms Usando Ruby
Infiltrando Telecoms Usando Ruby
 
Enhancing FreePBX with Adhearsion
Enhancing FreePBX with AdhearsionEnhancing FreePBX with Adhearsion
Enhancing FreePBX with Adhearsion
 
Connecting Adhearsion
Connecting AdhearsionConnecting Adhearsion
Connecting Adhearsion
 
Testing Adhearsion Applications
Testing Adhearsion ApplicationsTesting Adhearsion Applications
Testing Adhearsion Applications
 
Testing Telephony: It's Not All Terrible
Testing Telephony: It's Not All TerribleTesting Telephony: It's Not All Terrible
Testing Telephony: It's Not All Terrible
 
Rayo for XMPP Folks
Rayo for XMPP FolksRayo for XMPP Folks
Rayo for XMPP Folks
 
Talking To Rails
Talking To RailsTalking To Rails
Talking To Rails
 
Building Real Life Applications with Adhearsion
Building Real Life Applications with AdhearsionBuilding Real Life Applications with Adhearsion
Building Real Life Applications with Adhearsion
 
Keeping It Realtime!
Keeping It Realtime!Keeping It Realtime!
Keeping It Realtime!
 
Integrating Voice Through Adhearsion
Integrating Voice Through AdhearsionIntegrating Voice Through Adhearsion
Integrating Voice Through Adhearsion
 
Infiltrating Telecoms Using Ruby
Infiltrating Telecoms Using RubyInfiltrating Telecoms Using Ruby
Infiltrating Telecoms Using Ruby
 

Recently uploaded

Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
Tatiana Kojar
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
Antonios Katsarakis
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
innovationoecd
 
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - HiikeSystem Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
Hiike
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
akankshawande
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
Zilliz
 
JavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green MasterplanJavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green Masterplan
Miro Wengner
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
Intelisync
 
SAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloudSAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloud
maazsz111
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Safe Software
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
Pixlogix Infotech
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc
 
Azure API Management to expose backend services securely
Azure API Management to expose backend services securelyAzure API Management to expose backend services securely
Azure API Management to expose backend services securely
Dinusha Kumarasiri
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
tolgahangng
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
ssuserfac0301
 
WeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation TechniquesWeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation Techniques
Postman
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
shyamraj55
 
Trusted Execution Environment for Decentralized Process Mining
Trusted Execution Environment for Decentralized Process MiningTrusted Execution Environment for Decentralized Process Mining
Trusted Execution Environment for Decentralized Process Mining
LucaBarbaro3
 

Recently uploaded (20)

Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
 
Presentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of GermanyPresentation of the OECD Artificial Intelligence Review of Germany
Presentation of the OECD Artificial Intelligence Review of Germany
 
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - HiikeSystem Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
 
JavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green MasterplanJavaLand 2024: Application Development Green Masterplan
JavaLand 2024: Application Development Green Masterplan
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
 
SAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloudSAP S/4 HANA sourcing and procurement to Public cloud
SAP S/4 HANA sourcing and procurement to Public cloud
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
 
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERPBest 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
 
Azure API Management to expose backend services securely
Azure API Management to expose backend services securelyAzure API Management to expose backend services securely
Azure API Management to expose backend services securely
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
 
WeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation TechniquesWeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation Techniques
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
 
Trusted Execution Environment for Decentralized Process Mining
Trusted Execution Environment for Decentralized Process MiningTrusted Execution Environment for Decentralized Process Mining
Trusted Execution Environment for Decentralized Process Mining
 

Using Asterisk to Create "Her"

  • 1. Using Asterisk to create “Her”
  • 2. CAN YOU SPEAK MAGIC? 2 Allison Smith Ben Klang as “Her”
  • 3. CAN YOU SPEAK MAGIC? 3
  • 4. CAN YOU SPEAK MAGIC? 3
  • 5. CAN YOU SPEAK MAGIC? ALL ABOUT “HER” 4 Allison
  • 6. CAN YOU SPEAK MAGIC? 5
  • 7. CAN YOU SPEAK MAGIC? HOW DOES THIS WORK IN ASTERISK •We have access to the same core tech •ASR: Automatic Speech Recognition •NLU: Natural Language Understanding •TTS: Text-to-Speech •API: Application Program Interfaces •But it’s not just about the tech •It has to be useful •It has to usable 6
  • 8. CAN YOU SPEAK MAGIC? USABILITY: “HER” PERSONALITY 7
  • 9. CAN YOU SPEAK MAGIC? CREATING “HER” PERSONALITY •What kind of assistant is she? •Straight, no-nonsense •Bubbly, friendly •Sassy, smart-mouthed •Relaxed, laid back •Energetic, excited •Sultry, provocative 8
  • 10. CAN YOU SPEAK MAGIC? WHY PERSONALITY MATTERS 9
  • 11. CAN YOU SPEAK MAGIC? HOW DOES “SHE” WORK? 10
  • 12. CAN YOU SPEAK MAGIC? INSIDE “HER” ASR Recognizing Researching API NLU Understanding 11 Responding TTS Input/Output Channel Voice
  • 13. CAN YOU SPEAK MAGIC? INSIDE “HER” ASR Recognizing Researching API NLU Understanding 12 Responding TTS Input/Output Channel Voice
  • 14. CAN YOU SPEAK MAGIC? RECOGNIZING •Different kinds of ASR •Dictation / Transcription •Grammar-based •Hotword •Biometrics / Identity •DTMF has its place •The Media Connection •MRCP •HTTP APIs 13
  • 15. CAN YOU SPEAK MAGIC? RECOGNIZING INTERFACES •MRCP + Streaming recognition = fastest response + MRCPv2 is SIP-based – Somewhat more complex – Mobile-app unfriendly •HTTP API + Mobile-friendly + Simple API – Record-and-upload = slower response 14
  • 16. CAN YOU SPEAK MAGIC? 15 ASR Vendors / MRCP HTTP Grammar Dictation Hotword Nuance ✓ ✓ ✓ ✓ ✓ Lumenvox ✓ ✓ Vestec ✓ ✓ ✓ AT&T Watson ✓ ✓ ✓ Google ✓ ✓
  • 17. CAN YOU SPEAK MAGIC? INSIDE “HER” ASR Recognizing Researching API NLU Understanding 16 Responding TTS Input/Output Channel Voice
  • 18. CAN YOU SPEAK MAGIC? GRAMMAR-BASED RECOG 17 Where would you like to go? Chicago Tell me the month and day you want to leave? August fifth Tell me the month and day you want to return? August eighth What can I help you with? Book a flight Where are you flying from? Atlanta
  • 19. CAN YOU SPEAK MAGIC? NATURAL LANGUAGE “Hm, I want to go to AstriCon in Las Vegas on October 21st for three days, and I want the last flight out.” ✓ Destination ✓ Departing Date ✓ Returning Date + Extra Constraint 18 ? Origin
  • 20. CAN YOU SPEAK MAGIC? INSIDE “HER” ASR Recognizing Researching API NLU Understanding 19 Responding TTS Input/Output Channel Voice
  • 21. CAN YOU SPEAK MAGIC? 20 Send a tweet… Check in at… What is the weather today? Get me a table for two… Who won the game last night? What is Google trading at? When is my next appointment?
  • 22. CAN YOU SPEAK MAGIC? ZZZZZZzzzzzz…… 20 Send a tweet… Check in at… What is the weather today? Get me a table for two… Who won the game last night? What is Google trading at? When is my next appointment?
  • 23. CAN YOU SPEAK MAGIC? 21 How much have we sold so far this month? How many sales reps are still in homes? How many callers are in the queue right now? Add my manager to this call When is my next open appointment slot?
  • 24. CAN YOU SPEAK MAGIC? INSIDE “HER” ASR Recognizing Researching API NLU Understanding 22 Responding TTS Input/Output Channel Voice
  • 25. CAN YOU SPEAK MAGIC? TEXT-TO-SPEECH •Choose your voice carefully •Voice DBs’ quality varies widely •Tone of voice imparts as much as content •Mix TTS with recorded audio •Consider context of user •Check prosody (rate, pitch, volume) •Structure answers similarly to questions •Give option to repeat •Speech Synthesis Markup 23
  • 26. CAN YOU SPEAK MAGIC? INSIDE “HER” ASR Recognizing Researching API NLU Understanding 24 Responding TTS Input/Output Channel Voice
  • 27. CAN YOU SPEAK MAGIC? BEYOND VOICE: GETTING VISUAL 25
  • 28. CAN YOU SPEAK MAGIC? MULTI-MODE APPS •Request information by voice •Receive information via screen •SMS •Web browser (WebRTC!) •Allow continued input from alternate source •Respond via mouse click *or* voice 26
  • 29. CAN YOU SPEAK MAGIC? 27
  • 30. CAN YOU SPEAK MAGIC? QUESTIONS? PS: ALLISON WANTS TO BE THE NEXT SIRI! 28