最近我需要弄清楚另一件事，将我的 assembly.ai 转录引擎连接到一个声音很大的前端。
第一步是请求访问启用了回声消除功能的麦克风。此功能内置于大多数现代浏览器中，有助于减少扬声器的反馈。
async function getmicrophonestream() {
const constraints = {
audio: {
echocancellation: true,
noisesuppression: true,
autogaincontrol: true
}
};
try {
const stream = await navigator.mediadevices.getusermedia(constraints);
return stream;
} catch (err) {
console.error('error accessing the microphone', err);
return null;
}
}
接下来，我们设置 web audio api 来处理音频流。这涉及创建 audiocontext 并连接各种节点，包括 dynamicscompressornode。
async function setupaudioprocessing(stream) {
const audiocontext = new audiocontext();
const source = audiocontext.createmediastreamsource(stream);
// create a dynamicscompressornode for additional processing
const compressor = audiocontext.createdynamicscompressor();
compressor.threshold.setvalueattime(-50, audiocontext.currenttime); // example settings
compressor.knee.setvalueattime(null, audiocontext.currenttime);
compressor.ratio.setvalueattime(null, audiocontext.currenttime);
compressor.attack.setvalueattime(null, audiocontext.currenttime);
compressor.release.setvalueattime(0.25, audiocontext.currenttime);
// connect nodes
source.connect(compressor);
compressor.connect(audiocontext.destination);
return { audiocontext, source, compressor };
}
最后，我们将音频处理设置与 web speech api 集成以执行语音识别。
async function startSpeechRecognition() {
const stream = await getMicrophoneStream();
if (!stream) return;
const { audioContext, source, compressor } = await setupAudioProcessing(stream);
const recognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();
recognition.continuous = true;
recognition.interimResults = true;
recognition.onresult = (event) => {
for (let i = event.resultIndex; i {
console.error('Speech recognition error', event.error);
};
recognition.start();
// Handle audio context resume if needed
if (audioContext.state === 'suspended') {
audioContext.resume();
}
return recognition;
}
// Start the speech recognition process
startSpeechRecognition();
希望您发现这很有用。
快乐编码！
蒂姆.