Here in their documentations, they said:
The onspeechstart property of the SpeechRecognition interface Fired when sound that is recognised by the speech recognition service as speech has been detected.
With that in mind why even when I cough or make some noises ( that definitely has not any meaning or speech on it ) SpeechRecognition.onspeechstart fires?
How can I track if the sound that is received is a speech or a noise?
This is a Bug of Web Speech API, Hope that Google fix it in future >>>