This document discusses Amazon's artificial intelligence and deep learning capabilities. It summarizes Amazon's AI services including Amazon Lex for building conversational bots, Amazon Polly for text-to-speech, and Amazon Rekognition for computer vision tasks like image moderation, facial analysis, and celebrity recognition. It also discusses Amazon's deep learning framework MXNet and partnerships with Intel for high performance and low cost AI and machine learning.
7. Complete
Solution
End to End
Speech to Intent
ASR+NLU integrated
into one API
Dialog Management
Native support &
maintains context
Text to Speech
Amazon Polly
integrated into API
Business Logic
Native integration with
AWS Lambda
Deployment
One click deployment
Security
Encrypted data in
transit & at rest
Scale
Completely managed
service
Analytics
Monitor and improve
8. Text and Speech Language Understanding
Speech
Recognition
Natural Language
Understanding
Powered by the same Deep Learning
technology as Amazon Alexa
9. Amazon Lex: Use Cases
Informational Bots
Manage everyday consumer requests
Application Bots
Build powerful interfaces to mobile applications
• News updates
• Weather information
• FAQs ….
• Book tickets
• Order food
• Manage bank accounts ….
Enterprise Productivity Bots
Streamline enterprise work activities
• Check sales numbers
• Marketing performance
• Inventory status ….
Internet of Things (IoT) Bots
Enable conversational interfaces for device interactions
• Wearables
• Appliances
• Auto ….
10. Use Case: Employee Assistance
File time off
Sure. Starting what date
July 1st
How many days do you
plan to take off?
Book a conference room
Sure. What time?
Tomorrow Noon
I found a room on the 2nd
floor. Should I book it?
Reduce employee time and effort in everyday tasks
11. Employee Assistance: Design
Welcome Intent
Conf Room IntentTime off Intent Expense
Report Intent
:Record time off
I will be out July 1st – July 10th
Add PTO in July
……
Utterances
Start Date: AMAZON.DATE
End Date: AMAZON.DATE
……
Slots
File time off
Book a conference room
Can you find a room for 10
Need a conf room for my meeting
Utterances
Conf Room: ConfRoomList
Time: AMAZON.DATE
Duration: AMAZON.NUMBER
Slots
Book a conference room
Create expense
report
12. Converts text
to life-like speech
47 voices 24 languages Low latency,
real time
Fully managed
Amazon Polly: Life-like Speech Service
Voice Quality & Pronunciation
1. Automatic, Accurate Text Processing
2. Intelligible and Easy to Understand
3. Add Semantic Meaning to Text
4. Customized Pronunciation
Articles and Blogs
Training and Education
Chatbots (Lex)
Game/Media Characters
13. Amazon Polly: Text To Speech Quality
Accurate text processing
• Ability of the system to interpret common text formats such as
abbreviations, numerical sequences, homographs etc.
Today's maximum for New York, NY is expected to be 72°F
A row broke out over who would row the boat
He moped around after his moped was stolen
I am content that the content for today’s event is ready
14. Whisper Voice and Speech Marks
Whisper SSML effect: <amazon:effect name="whispered">
Synchronize Speech for an Enhanced Visual Experience
• Request an additional stream of metadata about
sentence word timings
• Use the metadata stream alongside the synthesized
speech audio stream to sync audio and visual