Three New Amazon Web Services (AWS) AI Technologies: Lex, Polly and Rekognition
Amazon offers three artificial intelligence services on Amazon Web Services (AWS); Lex, Polly and Rekognition. These new services give developers more tools to engage with customers.
Technology advancements have made these services possible through a combination of better algorithms and broad access to massive amounts of data and cost-effective computing power.
- Lex is the technology that powers Amazon Alexa and allows developers to integrate rich conversational experiences into their offerings.
- Polly is a state-of-the-art text to speech service that has forty-seven life like voices in twenty languages.
- Rekognition is an image and video processing service, that can identify content.
Lex is the machine learning technologies that powers Amazon Alexa, with the key components being Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU).
Lex can be used by developers to quickly make chat and voice bots that can be integrated into services and applications. Lex is deployed as a fully managed service, requiring little time to set up, administer, and scale.
Lex has an integrated development environment in a console. Developers can create bots, test them, and deploy them through the Lex interface. Amazon provides sample bots to help you get started.
Bots built using Lex can be used on multiple platforms, and Amazon handles the authentication processes for different platforms. Lex can connect with Facebook Messenger, Slack, and Twilio.
In 2018 Lex service is charged at the rate of $4 for 1000 speech requests, and $0.75 for 1000 text requests.
Amazon Lex provides developers with an easy-to-use modular architecture and comprehensive APIs for building and deploying conversational bots on mobile platforms.
Polly is a cloud-based text to speech service that generates synthetic speech from text strings. Speech Synthesis Markup Language (SSML) is supported for advanced functionality, such as mixed language text. Developers can use SSML let Polly know that some words in an English sentence are in French. There is a vast language and region menu, with support for five regional accents of English, including Indian.
The SDK and console can be used to send text to Polly. Polly converts text-to-speech in the cloud and returns the results back to the application. The service can be integrated into a broad range of applications such as e-book readers, personal assistants, entertainment apps, public service announcement systems, and e-learning platforms.
Polly is optimized to handle high volumes of text-to-speech rapidly. Amazon Polly has high-quality voices that offer a more rich and versatile ways to experience online content.
Amazon Rekognition is a service for building a new generation of apps that have human-like intelligence and can see, hear, speak, and interact with people and their environments.
Rekognition is an artificial intelligence image and video analysis service. Rekognition can be used to recognise faces, objects and scenes in an image. The AI service delivers a confidence score for each identification, which is a rating of how accurate the identification is likely to be. These confidence scores can be further processed by an app or service. Rekognition has advanced facial analysis functions such as face comparison, and face search.
Some of the capabilities of Rekognition include assessing if the mouth of a person is open or closed, whether or not they are smiling, if they are happy, whether they are wearing sunglasses, and can identify the presence or absence of facial hair.
Rekognition can be applied to enhance security services, smart marketing implementations that track user engagements, and automate the indexing and tagging of vast image or video libraries.
The three new AI Amazon Web Services are scalable and cost effective, with developers paying for only what they use.
Amazon has simplified access to neural networks, data required for training, and expertise in machine learning. The heavy lifting is done by Amazon, with the artificial intelligences trained for a wide variety of scenarios.
Developers can start using the AI without building machine learning algorithms, training the AI with models, or commit to infrastructure investments upfront.