📅  最后修改于: 2022-03-11 14:58:10.439000             🧑  作者: Mango
const magic_word = ##YOUR_MAGIC_WORD##;
// initialize our SpeechRecognition object
let recognition = new webkitSpeechRecognition();
recognition.lang = 'en-US';
recognition.interimResults = false;
recognition.maxAlternatives = 1;
recognition.continuous = true;
// detect the magic word
recognition.onresult = e => {
// extract all the transcripts
var transcripts = [].concat.apply([], [...e.results]
.map(res => [...res]
.map(alt => alt.transcript)
)
);
if(transcripts.some(t => t.indexOf(magic_word) > -1)){
//do something awesome, like starting your own command listeners
}
else{
// didn't understood...
}
}
// called when we detect silence
function stopSpeech(){
recognition.stop();
}
// called when we detect sound
function startSpeech(){
try{ // calling it twice will throw...
recognition.start();
}
catch(e){}
}
// request a LocalMediaStream
navigator.mediaDevices.getUserMedia({audio:true})
// add our listeners
.then(stream => detectSilence(stream, stopSpeech, startSpeech))
.catch(e => log(e.message));
function detectSilence(
stream,
onSoundEnd = _=>{},
onSoundStart = _=>{},
silence_delay = 500,
min_decibels = -80
) {
const ctx = new AudioContext();
const analyser = ctx.createAnalyser();
const streamNode = ctx.createMediaStreamSource(stream);
streamNode.connect(analyser);
analyser.minDecibels = min_decibels;
const data = new Uint8Array(analyser.frequencyBinCount); // will hold our data
let silence_start = performance.now();
let triggered = false; // trigger only once per silence event
function loop(time) {
requestAnimationFrame(loop); // we'll loop every 60th of a second to check
analyser.getByteFrequencyData(data); // get current data
if (data.some(v => v)) { // if there is data above the given db limit
if(triggered){
triggered = false;
onSoundStart();
}
silence_start = time; // set it to now
}
if (!triggered && time - silence_start > silence_delay) {
onSoundEnd();
triggered = true;
}
}
loop();
}