Hey, Satya!

Automatic Speech Recognition Inference

ASR Engine

You can use the ASR Engine below to run automatic speech recognition using Microsoft Azure's Cognitive Service's Speech API. You will need to sign up for a subscription key. Alternatively, you can use my key which has been filled in for you.

I have not yet found an elegant solution for allowing you to interface with the Hey, Satya! model for ASR.

Note: This relies on Microsoft's SDK which depends on WebRTC APIs to get access to the microphone and read the audio stream. Most of todays browsers(Edge/Chrome/Firefox) support this. The SDK currently depends on the JavaScript navigator.getUserMedia API. However this API is in the process of being dropped as browsers are moving towards the newer MediaDevices.getUserMedia. The SDK should add support for the newer API soon but this means that this engine may not work for you. If it doesn't, please try it in a different browser.

Speech Recognition SDK not compatible with your browser.

Microsoft Cognitive Services

Recognition Mode:

Note: Audio files must be in WAVE/WAV format (file extension must be '.wav') and no more than 10 seconds in length. The audio file must be encoded in PCM single channel (mono).The bit rate must be at least 64k, and the sample rate must be 16000Hz (16Khz). The max frequency cannot be more than 16000Hz. You can record using your microphone with a tool like Audacity.


Current hypothesis: