Focus on this objective today: Identify AI workloads: Identify features and capabilities of speech recognition and speech synthesis. Explain it in your own words, apply it to one realistic scenario, and verify the details against the official source. Source context: Read in English Create an image recognition solution with Azure IoT Edge, Azure AI Custom Vision, and Azure Speech Module 9 Units Feedback Intermediate AI Edge Engineer Azure IoT Edge Azure IoT Hub Azure AI Custom Vision Azure Speech in Foundry Tools Foundry Tools Build an Azure IoT Edge image recognition solution for a self-checkout scenario. The exported Azure AI Custom Vision classification model runs locally in an IoT Edge module, and the Camera Capture module calls Azure Speech (via a Foundry resource) at runtime to synthesize item labels as audio. Learning objectives In this module, you will: Describe how Azure IoT Edge, Azure IoT Hub, a camera, and containerized modules support image recognition at the edge Use a prebuilt, exported Azure AI Custom Vision classification model packaged in an IoT Edge module Create the required Azure resources, including an IoT Hub device identity and a Foundry resource for Speech in Southeast Asia, unless you update the sample code and deployment template to make the Speech region configurable Build and deploy the solution to an Azure IoT Edge device by using Visual Studio Code Verify module status and monitor events from the edge device and Azure IoT Hub Note This lab uses the Azure IoT Edge tools for Visual Studio Code extension because the existing lab assets and steps depend on that workflow.
Objective
Identify AI workloads: Identify features and capabilities of speech recognition and speech synthesis