37. Polly API example
aws polly synthesize-speech
--text "It was nice to live such a wonderful live show"
--output-format mp3
--voice-id Joanna
--text-type text johanna.mp3
aws polly synthesize-speech
--text-type ssml
--text file://ssml_polly
--output-format mp3
--voice-id Joanna speech.mp3
38. “With Amazon Polly our users benefit from
the most lifelike Text-to-Speech voices
available on the market.”
Severin Hacker
CTO, Duolingo
52. Fully managed natural language processing
Discover valuable insights from text
Entities
Key Phrases
Language
Sentiment
Amazon
Comprehend
53. Support for large data sets and topic modeling
STORM
WORLD SERIES
STOCK MARKET
WASHINGTON
LIBRARY OF
NEW S ARTICLES *
Amazon
Comprehend
* Integrated with Amazon S3 and AWS Glue
59. Intents
A particular goal that the
user wants to achieve
Utterances
Spoken or typed phrases
that invoke your intent
Slots
Data the user must provide to fulfill the
intent
Prompts
Questions that ask the user to input
data
Fulfillment
The business logic required to fulfill the
user’s intent
BookHotel
73. AWS Deep Learning AMI
• Easy-to-launch tutorials
• Hassle-free setup and configuration
• Pay only for what you use
• Accelerate your model training and deployment
• Support for popular deep learning frameworks
So the 20 years and thousands of engineers we’ve had working on Amazon have helped drive operation efficiencies and better experiences for our customers.. And that experience and the tools we have developed, we offer them for you to build and innovate with.
Amazon Robotics was founded in 2003 on the notion that in order to meet consumer demands in eCommerce, a better approach to order fulfillment solutions was necessary. Amazon Robotics empowers a smarter, faster, more consistent customer experience through automation
automates fulfilment center operations using various methods of robotic technology including autonomous mobile robots, sophisticated control software, language perception, power management, computer vision, depth sensing, machine learning, object recognition, and semantic understanding of commands.
Alexa is fueled by Natural Language Understanding and Automated Speech Recognition deep learning;
Amazon Prime Air is a service that will deliver packages up to 2.5 kg in 30 minutes or less using small drones and relies extensively on visual object recognition.
We have Prime Air development centers in the United States, the United Kingdom, Austria, France and Israel.
as is our drone initiative, Prime Air, and the computer vision technology in our new retail experience, Amazon Go. We have thousands of engineers at Amazon committed to machine learning and deep learning, and it’s a big part of our heritage.
Amazon Go is a new kind of store with no checkout required. We created the world’s most advanced shopping technology so you never have to wait in line. With our Just Walk Out Shopping experience, simply use the Amazon Go app to enter the store, take the products you want, and go! No lines, no checkout. (No, seriously.)
No lines, no checkout
Our checkout-free shopping experience is made possible by the same types of technologies used in self-driving cars: computer vision, sensor fusion, and deep learning. Our Just Walk Out Technology automatically detects when products are taken from or returned to the shelves and keeps track of them in a virtual cart. When you’re done shopping, you can just leave the store. Shortly after, we’ll charge your Amazon account and send you a receipt.
as is our drone initiative, Prime Air, and the computer vision technology in our new retail experience, Amazon Go
From A to Z – Artfinder to Zillow
Duolingo
Cspan
Slactwilio
Mapbox
Pinterest
finra
Amazon Rekognition currently supports the JPEG and PNG image formats. You can submit images either as an S3 object or as a byte array.Amazon Rekognition supports image file sizes up to 15MB when passed as an S3 object, and up to 5MB when submitted as an image byte array.Amazon Rekognition is currently available in US East (Northern Virginia), US West (Oregon) and EU (Ireland) regions.
Mxnet convolutional deep neural networks (CNNs),
You can use the ‘MinConfidence’ parameter in your API requests to balance detection of content (recall) vs the accuracy of detection (precision).
You can use the ‘MinConfidence’ parameter in your API requests to balance detection of content (recall) vs the accuracy of detection (precision).
…Amazon Rekognition Video, a new video recognition service powered by deep learning. 1/ Video Rek lets you pass videos to us using our APIs or SDK and will detect all sorts of things in the video
2/ Will detect, objects, faces, scenes (like delivering a pkg so app can take action on that), celebs, inappropriate content
3/ Person tracking a unique feature and powerful…lets you track person even if their face becomes blocked or leaves the frame and returns…do this through Skeleton Modeling…can tell when still in the scene and even the direction the person is heading…useful for apps that give system access when person in a room and shut down when out.
1/ Service really easy to use
2/ Can handle missions of videos you have stored in S3 via batch processing
3/ Can process real time video (NO OTHER SERVICE CAN DO)…enables a lot of apps where you want to take action on what’s happening now
4/ Service automatically time-stamps everything it identifies
5/ Service will keep getting better b/c of sheer vol of data we have with internal and public datasets
6/ Very cost effective
…Amazon Kinesis Video Streams, a new service to securely ingest and store video, audio and other time-encoded data <PAUSE FOR CLAPPING>
1/ Just like Kinesis for data that lets you ingest and store data, Kinesis Video Stream does same for video and other time-encoded data like radar
2/ Provides SDKs for device mfrs to install on devices to make easy to stream video to AWS
3/ Durably, stores, encrypts and indexes data streams along with easy to use API so that apps can access and retrieve video fragments based on tags or timestamps
4/ Integrated with Video Rekognition so can ingest data and then do analytics
"Amazon Rekognition's new video analytic features are impressive. They can, for example, help with search of historical and real time video for persons-of-interest, providing efficiencies and awareness by automating this typically human task."
Dan Law, Chief Data Scientist
"The City of Orlando is excited to work with Amazon to pilot the latest in public safety software through a unique, first-of-it's-kind public-private partnership. Through the pilot, Orlando will utilize Amazon’s Rekognition Video and Amazon Kinesis Video Streams technology in a way that will use existing City resources to provide real-time detection and notification of persons-of-interests, further increasing public safety, and operational efficiency opportunities for the City of Orlando and other cities across the nation.
John Mina Police Chief, City of Orlando
Polly also support Speech Synthesis Markup Language (SSML) Version 1.0
The Voice Browser Working Group has sought to develop standards to enable access to the Web using spoken interaction.
Spoken language crucial for language learning
Accurate pronunciation matters
Faster iteration thanks to TTS
As good as natural human speech
When teaching a foreign language, accurate pronunciation matters. If exposed to incorrect pronunciation, learners develop their listening and speaking skills poorly, which compromises their ability to communicate effectively. Duolingo uses text-to-speech (TTS) to provide high-quality language education. To some, this approach might seem counterintuitive: shouldn’t people learn by listening to a native speaker?
Find a company that records audio in the language: The company must find a voice actor who not only speaks the language, but also who speaks with good pronunciation and clarity.
Find someone to evaluate the quality of pronunciation: We need an independent party from the recording company to create a small sample of sentences, which this party uses to evaluate pronunciation quality of the recordings.
Record and evaluate the quality of the sample sentences.
Set up a contract with the recording company.
Record all sentences.
Evaluate recordings, providing a data quality assurance check. For example, we need to check if all files are in the proper format and correctly separated. This step is necessary because the industry standard is to record all sentences in a single session and separate them later.
“Providing locally relevant personalized travel experiences is the goal at Hotels.com. Hence helping our customers find the right experience is crucial. Amazon Comprehend helps us analyze the key sentiments, objects, and geos in our 30 million plus reviews & testimonies. Now we are able to discover new insights into the unique experiences available at each property, so our customers can make the best decision possible for their travel.”
– Matt Fryer, VP and Chief Data Science Officer of Hotels.com and Expedia Affiliate Network
“RingDNA is an end-to-end communications platform for sales teams. Hundreds of enterprise organizations use RingDNA to dramatically increase productivity, engage in smarter sales conversations, gain predictive sales insights, improve their win rate and coach reps to success faster than ever before. A critical component of RingDNA’s Conversation AI requires best of breed speech-to-text to deliver transcriptions of every phone call. RingDNA is excited about Amazon Transcribe since it provides high-quality speech recognition at scale, helping us to better transcribe every call to text.”Howard Brown – CEO & Founder, RingDNA
“At Isentia, we enable customers to analyze and monitor the media coverage for their brands. We create more than 13K summaries per day from radio and TV content. With Amazon Transcribe, we can transcribe all the audio/video content that we monitor and analyze the text data with Amazon Comprehend. Features like timestamps and punctuation make it very easy for us to search through the data and drill down and present key insights for our customers to review."Andrea Walsh - CIO, Isentia
…Amazon Comprehend, a Natural Language Processing service that enables customers to discover insights from text.
1/ Without provisioning a server, Comprehend can understand documents, social network posts, articles, and any other data in AWS
2/ Simply provide text stored in data lake in S3 via Comprehend API, and Comprehend uses NLP to give you highly accurate info about what it contains in 4 categories:
a/ entities (people, places, dates, brands, qtys)
b/ key phrases that provide significance to the text
c/ language being used
d/ sentiment
1/ Comprehend also has the unique ability to not just look at a single document at a time but to look at millions in order to identify the topics within these docs—we call this TOPIC MODELING
2/ Publisher org articles by subject matter; healthcare by symptom or diagnosis
3/ Comprehend does this in an incredibly efficient manner…For ex, for 300 docs, each around 1MB in size, Comprehend can build a custom topic model in 45 mins for $1.80
4/ Makes it much easier and cost effective to build more intelligent models and actions out of all this data sitting in text
1/ Comprehend also has the unique ability to not just look at a single document at a time but to look at millions in order to identify the topics within these docs—we call this TOPIC MODELING
2/ Publisher org articles by subject matter; healthcare by symptom or diagnosis
3/ Comprehend does this in an incredibly efficient manner…For ex, for 300 docs, each around 1MB in size, Comprehend can build a custom topic model in 45 mins for $1.80
4/ Makes it much easier and cost effective to build more intelligent models and actions out of all this data sitting in text
Providing locally relevant personalized travel experiences is the goal at Hotels.com. Hence helping our customers find the right experience is crucial. Amazon Comprehend helps us analyze the key sentiments, objects, and geos in our 30 million plus reviews & testimonies. Now we are able to discover new insights into the unique experiences available at each property, so our customers can make the best decision possible for their travel.”
– Matt Fryer, VP and Chief Data Science Officer of Hotels.com and Expedia Affiliate Network
“Building intelligent applications to help customers drive their businesses is our entire focus. Amazon Comprehend allows us to analyze unstructured text within search, chat, and documents to understand intent and sentiment. This capability enables us to train our Coleman AI skillset, and also provide a truly focused and tailored search experience for our customers.” – Manjunath Ganimasty, V.P. Software Development with Infor
“The Post strives to give its nearly 100 million readers the best experience possible and relevant content recommendations are a key part of that mission. With Amazon Comprehend, we can leverage the continuously-trained NLP capabilities like Keyphrase and Topic APIs to potentially allow us to provide even better content personalization, SEO, and ad targeting capabilities.”
The insight that lies in unstructured text - blogs, social media posts and comments, provides an enormous resource for businesses. This intelligence can be used by our clients to better connect with their customers. For Isentia, using Amazon Comprehend in conjunction with the diverse range of AWS analytics services has enabled us to provide rich information to our clients who can, in turn, develop tailored messages that resonate with customers and deliver results.”
– Andrea Walsh, CIO, Isentia
Apache Spark and Spark ML overview
Running Spark ML on Amazon EMR
Interactive notebook options
Building recommendation engines at Zillow Group
Zillow Group uses machine-learning to deliver near-real-time home-valuation data to customers using AWS. The company houses a portfolio of the largest online real-estate and home-related brands. Zillow Group runs the Zestimate, its machine learning–based home-valuation tool, on Amazon Kinesis and Apache Spark on Amazon EMR.
Pre-built Notebook Instances
For training data exploration and preprocessing, Amazon SageMaker provides fully managed notebook instances running Jupyter notebooks that include example code for common model training and hosting exercises. These notebook instances are pre-loaded with Anaconda packages, and popular deep learning libraries like TensorFlow, and Apache MXNet.
Highly-optimized Machine Learning Algorithms
Amazon SageMaker installs high-performance, scalable machine learning algorithms optimized for speed, scale, and accuracy, to run on extremely large training datasets. Based on the type of learning that you are undertaking, you can choose from supervised algorithms, such as linear/logistic regression or classification; as well as unsupervised learning, such as with k-means clustering.
TRAIN
One-click Training
When you’re ready to train in Amazon SageMaker, simply indicate the type and quantity of instances you need and initiate training with a single click. SageMaker sets up the distributed compute cluster, performs the training, and tears down the cluster when complete. SageMaker seamlessly scales to tens of nodes with hundreds of GPUs, so you no longer need to worry about all the complexity and lost time involved in making distributed training architectures work.
Built-in Automatic Hyperparameter Optimization (in Preview)
Using built-in hyperparameter optimization (HPO), SageMaker can automatically tune your algorithm by adjusting hundreds of different combinations of parameters, to quickly arrive at the best solution for your machine learning problem. HPO lets you easily optimize an ML model on SageMaker by exploring lots of variations of the same algorithm with varying hyperparameters to pick the one with the best performance on your data.
DEPLOY
Deployment without Engineering Effort
After training, SageMaker provides the model artifacts and scoring images to you for deployment to Amazon EC2 or anywhere else. When you’re ready to deploy your model, you can launch into a secure and elastically scalable environment, with one-click deployment from the SageMaker console.
Fully Managed
Amazon SageMaker handles all of the compute infrastructure on your behalf, with built-in Amazon CloudWatch monitoring and logging, to perform health checks, apply security patches, and other routine maintenance, as well as ensure updates to the supported deep learning frameworks as they become available.
Tons of companies across industries doing Machine Learning on their own; but it’s still very very early, and most companies don’t yet have deep knowledge or experienced practitioners on board.
Customers are coming to us with: “Can Amazon bring their experience in ML to quickly help our company unlock business value via routine use of ML?” and “Can Amazon impart hands-on knowledge in ML to our developers?”
Amazon ML Lab unites machine learning experts from Amazon with our customers wanting help with:
Problem Solving – via brainstorming, data preparation, annotation, custom modeling, application services (Lex, Polly, Rekognition)
Education – via workshops and tutorials
These ML experts are the brains behind innovative, machine learning based products and technologies of the future at Amazon such as Amazon Echo, Amazon Alexa, autonomous delivery through Prime Air, or Amazon Go
Who can use the Amazon AI Lab?
The Amazon AI Lab is available to customers with AWS Business Support or AWS Enterprise Support.
Is this a professional services engagement?
Yes, in part. An Amazon AI Lab partnership also includes a significant amount of education and training, to allow developers to take what they have learned through the process and use it elsewhere in their organization. We will also provide guidance on change management for ML, establishing ‘centers of excellence’ for machine learning, and we will provide materials for further on-site training. Similar to a professional services agreement, AI Lab engagements will require a contract and will have defined deliverables (such as a completed proof of concept or trained model integrated with a production system).
What is AI Lab Express?AI Lab Express is a four-week accelerated program which brings enterprise developers on-site with Amazon machine learning experts for an intensive boot camp (typically one week), followed by guidance and hands-on implementation with custom modeling and production deployment advice. It’s designed for customers who have already established a relevant data lake and data catalog, and who already have a large volume of high quality, trusted, labeled data available for modeling. The primary goal with AI Lab Express is to work with the customer on feature engineering, and to build models quickly through Amazon SageMaker.
How long is the usual AI Lab engagement?Amazon AI Lab partnerships typically last from 3 to 6 months.
So far, we've discussed the bottom and middle layers of the machine learning stack – first we talked about the frameworks and the deep learning AMI for expert practitioners. Then, SageMaker and DeepLens in the middle layer to bring ML capabilities to all developers. Now, at the top of the stack, we serve developers and companies who want to add solution-oriented intelligence to their applications through an API call rather than developing and training their own models. These are services that exhibit artificial intelligence that emulates a human’s cognitive skills. Last year, we announced three services in this area: Amazon Rekognition (image analysis), Amazon Polly (text-to-speech), and Amazon Lex (conversational applications).