{"id":2796,"date":"2021-06-22T23:18:01","date_gmt":"2021-06-22T23:18:01","guid":{"rendered":"https:\/\/wordpress-634681-2064240.cloudwaysapps.com\/?p=2796"},"modified":"2021-06-25T11:14:11","modified_gmt":"2021-06-25T11:14:11","slug":"azure-percept-audio-first-steps","status":"publish","type":"post","link":"https:\/\/www.petecodes.co.uk\/azure-percept-audio-first-steps\/","title":{"rendered":"Azure Percept Audio – First Steps"},"content":{"rendered":"\n
In the first post in this series<\/a> we took a first look at the Azure Percept and it’s primary components.<\/p>\n\n\n\n In this post we’ll take a look at the Azure Percept Audio Module, which allows for the recognition of Custom Keywords and Commands.<\/p>\n\n\n\n The Azure Percept Audio is a System on a Module (SoM), which is designed as the Audio Interface for Audio Processing at the edge for the Azure Percept.<\/p>\n\n\n\n Along with the Carrier Board, Azure Percept Studio, Microsoft LUIS and Speech, the system can recognise keywords and commands to control devices using voice at the edge. This works both online and offline with the aid of the Carrier Board.<\/p>\n\n\n\n The basic specs for the Azure Percept Audio SoM are;<\/p>\n\n\n\n You can find the full specifications here<\/a><\/p>\n\n\n\n Microsoft have a set of industries in mind for the Azure Percept Audio SoM;<\/p>\n\n\n\n With applications such as;<\/p>\n\n\n\n The Azure Percept Audio SoM makes use of a couple of Azure Services to process Audio.<\/p>\n\n\n\n LUIS is an Azure service which allows interaction with applications and devices using natural language.<\/p>\n\n\n\n Using a visual interface, we’re able to train AI models without the need for deep Machine Learning experience of any kind.<\/p>\n\n\n\n The Azure Percept uses LUIS to configure Custom Commands, allowing for a contextualised response to a given command.<\/p>\n\n\n\n Cognitive Speech is an Azure Service offering Text-to-speech, speech-to-text, speech translation and speaker recognition.<\/p>\n\n\n\n Supporting over 92 languages, this service can convert speech to text allowing for interactivity with apps and devices.<\/p>\n\n\n\n On the flip side, with support for over 215 different voices in 60 languages, the Speech Service can also convert Text to-Speech improving accessibility and interaction with devices and applications.<\/p>\n\n\n\n Finally, the Speech Service can also translate between 30 different languages, allowing for real-time translation using a variety of programming languages.<\/p>\n\n\n\n The Percept uses this service amongst other things, to configure a wake word for the device, by default this is the word “computer<\/em><\/strong>“. (See Star Trek IV – The Voyage Home!).<\/p>\n\n\n\n If we navigate to Azure Percept Studio<\/a>, from the Overview Page we can select the “Demos & tutorials” tab at the top;<\/p>\n\n\n\n If we scroll to the bottom of this page, we have some links to some Speech tutorials and demos.<\/p>\n\n\n\n The first thing we’ll choose is “Try out voice assistant templates”. Clicking this link presents us with a fly out with a selection of templates to choose from;<\/p>\n\n\n\n Choosing the “Hospitality” option, agreeing to the terms and continuing on, we’re shown the resource creation flyout.<\/p>\n\n\n\n Here we can select the subscription and resource group we’d like to deploy the various resources to.<\/p>\n\n\n\n We’re also prompted for an Application Prefix. This allows the template to create resources with unique ids.<\/p>\n\n\n\n We can then choose a region close to us. At the time of writing we can choose between West US and West Europe.<\/p>\n\n\n\n Finally, we can leave the “LUIS prediction pricing tier” at “Standard”, as the free tier doesn’t support speech requests.<\/p>\n\n\n\n Hitting the “Create” button, then begins the process of deploying the speech theme resources.<\/p>\n\n\n\n We’re then prompted that this process can take between 2 and 4 minutes to complete….<\/p>\n\n\n\nAzure Percept Audio<\/h2>\n\n\n\n
Azure Percept Audio Specifications<\/h2>\n\n\n\n
Target Industries<\/h2>\n\n\n\n
Azure Percept Audio – Required Azure Services<\/h2>\n\n\n\n
LUIS (Language Understanding Intelligent Service)<\/h3>\n\n\n\n
Cognitive Speech<\/h3>\n\n\n\n
Azure Percept Audio – Sample Applications<\/h2>\n\n\n\n
Azure Percept Audio – Hospitality Sample Template Setup<\/h2>\n\n\n\n