本文主要是介绍使用代码录音的三种方案(js,java和C#)，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
最近在做语音识别有关的内容，但是语音是被之前需要进行录音，因为一些情况，我分别调研了js录音，java录音，C#录音的三种方式，下面简单的粘贴一下录音代码
C#录音工具类
using Microsoft.DirectX.DirectSound;
using System;
using System.Collections.Generic;
using System.IO;
using System.Text;
using System.Threading;
using System.Windows.Forms;namespace SelfServiceMachines
{public class SoundRecord {#region 成员数据private Capture mCapDev = null; // 音频捕捉设备private CaptureBuffer mRecBuffer = null; // 缓冲区对象private WaveFormat mWavFormat; // 录音的格式private int mNextCaptureOffset = 0; // 该次录音缓冲区的起始点private int mSampleCount = 0; // 录制的样本数目private Notify mNotify = null; // 消息通知对象public const int cNotifyNum = 16; // 通知的个数private int mNotifySize = 0; // 每次通知大小private int mBufferSize = 0; // 缓冲队列大小private Thread mNotifyThread = null; // 处理缓冲区消息的线程private AutoResetEvent mNotificationEvent = null; // 通知事件private string mFileName = string.Empty; // 文件保存路径private FileStream mWaveFile = null; // 文件流private BinaryWriter mWriter = null; // 写文件#endregionpublic SoundRecord() {//初始化音频捕捉设备 InitCaptureDevice();//设定录音格式 mWavFormat = CreateWaveFormat();}#region 对外操作函数/// <summary> /// 创建录音格式,此处使用16bit,16KHz,Mono的录音格式 /// <summary> private WaveFormat CreateWaveFormat() {WaveFormat format = new WaveFormat();format.FormatTag = WaveFormatTag.Pcm; // PCM format.SamplesPerSecond = 16000; // 采样率：16KHz format.BitsPerSample = 16; // 采样位数：16Bit format.Channels = 1; // 声道：Mono format.BlockAlign = (short) ( format.Channels * ( format.BitsPerSample / 8 ) ); // 单位采样点的字节数 format.AverageBytesPerSecond = format.BlockAlign * format.SamplesPerSecond;return format;// 按照以上采样规格，可知采样1秒钟的字节数为 16000*2=32000B 约为31K }/// <summary> /// 设定录音结束后保存的文件,包括路径 /// </summary> /// <param name="filename">保存wav文件的路径名</param> public void SetFileName(string filename) {mFileName = filename;}/// <summary> /// 开始录音 /// </summary> public void RecStart() {// 创建录音文件 CreateSoundFile();// 创建一个录音缓冲区，并开始录音 CreateCaptureBuffer();// 建立通知消息,当缓冲区满的时候处理方法 InitNotifications();mRecBuffer.Start(true);}/// <summary> /// 停止录音 /// </summary> public void RecStop() {mRecBuffer.Stop(); // 调用缓冲区的停止方法，停止采集声音 if (null != mNotificationEvent)mNotificationEvent.Set(); //关闭通知 mNotifyThread.Abort(); //结束线程 RecordCapturedData(); // 将缓冲区最后一部分数据写入到文件中 // 写WAV文件尾 mWriter.Seek(4, SeekOrigin.Begin);mWriter.Write((int) ( mSampleCount + 36 )); // 写文件长度 mWriter.Seek(40, SeekOrigin.Begin);mWriter.Write(mSampleCount); // 写数据长度 mWriter.Close();mWaveFile.Close();mWriter = null;mWaveFile = null;}#endregion#region 对内操作函数/// <summary>/// 初始化录音设备,此处使用主录音设备./// </summary>/// <returns>调用成功返回true,否则返回false</returns>private bool InitCaptureDevice() {//获取默认音频捕捉设备CaptureDevicesCollection devices = new CaptureDevicesCollection(); // 枚举音频捕捉设备Guid deviceGuid = Guid.Empty;if (devices.Count > 0)deviceGuid = devices[0].DriverGuid;else {MessageBox.Show("系统中没有音频捕捉设备");return false;}// 用指定的捕捉设备创建Capture对象try {mCapDev = new Capture(deviceGuid);} catch (Microsoft.DirectX.DirectXException e) {//MessageBox.Show(e.ToString());return false;}return true;}/// <summary>/// 创建录音使用的缓冲区/// </summary>private void CreateCaptureBuffer() {// 缓冲区的描述对象CaptureBufferDescription bufferdescription = new CaptureBufferDescription();if (null != mNotify) {mNotify.Dispose();mNotify = null;}if (null != mRecBuffer) {mRecBuffer.Dispose();mRecBuffer = null;}// 设定通知的大小,默认为1s钟mNotifySize = ( 1024 > mWavFormat.AverageBytesPerSecond / 8 ) ? 1024 : ( mWavFormat.AverageBytesPerSecond / 8 );mNotifySize -= mNotifySize % mWavFormat.BlockAlign;// 设定缓冲区大小mBufferSize = mNotifySize * cNotifyNum;// 创建缓冲区描述bufferdescription.BufferBytes = mBufferSize;bufferdescription.Format = mWavFormat; // 录音格式// 创建缓冲区mRecBuffer = new CaptureBuffer(bufferdescription, mCapDev);mNextCaptureOffset = 0;}/// <summary>/// 初始化通知事件,将原缓冲区分成16个缓冲队列,在每个缓冲队列的结束点设定通知点./// </summary>/// <returns>是否成功</returns>private bool InitNotifications() {if (null == mRecBuffer) {// MessageBox.Show("未创建录音缓冲区");return false;}// 创建一个通知事件,当缓冲队列满了就激发该事件.mNotificationEvent = new AutoResetEvent(false);// 创建一个线程管理缓冲区事件if (null == mNotifyThread) {mNotifyThread = new Thread(new ThreadStart(WaitThread));mNotifyThread.Start();}// 设定通知的位置BufferPositionNotify[] PositionNotify = new BufferPositionNotify[cNotifyNum + 1];for (int i = 0; i < cNotifyNum; i++) {PositionNotify[i].Offset = ( mNotifySize * i ) + mNotifySize - 1;PositionNotify[i].EventNotifyHandle = mNotificationEvent.SafeWaitHandle.DangerousGetHandle();}mNotify = new Notify(mRecBuffer);mNotify.SetNotificationPositions(PositionNotify, cNotifyNum);return true;}/// <summary>/// 接收缓冲区满消息的处理线程/// </summary>private void WaitThread() {while (true) {// 等待缓冲区的通知消息mNotificationEvent.WaitOne(Timeout.Infinite, true);// 录制数据RecordCapturedData();}}/// <summary>/// 将录制的数据写入wav文件/// </summary>private void RecordCapturedData() {byte[] CaptureData = null;int ReadPos = 0, CapturePos = 0, LockSize = 0;mRecBuffer.GetCurrentPosition(out CapturePos, out ReadPos);LockSize = ReadPos - mNextCaptureOffset;if (LockSize < 0) // 因为是循环的使用缓冲区，所以有一种情况下为负：当文以载读指针回到第一个通知点，而Ibuffeoffset还在最后一个通知处LockSize += mBufferSize;LockSize -= ( LockSize % mNotifySize ); // 对齐缓冲区边界,实际上由于开始设定完整,这个操作是多余的.if (0 == LockSize)return;// 读取缓冲区内的数据CaptureData = (byte[]) mRecBuffer.Read(mNextCaptureOffset, typeof(byte), LockFlag.None, LockSize);// 写入Wav文件mWriter.Write(CaptureData, 0, CaptureData.Length);// 更新已经录制的数据长度.mSampleCount += CaptureData.Length;// 移动录制数据的起始点,通知消息只负责指示产生消息的位置,并不记录上次录制的位置mNextCaptureOffset += CaptureData.Length;mNextCaptureOffset %= mBufferSize; // Circular buffer}/// <summary>/// 创建保存的波形文件,并写入必要的文件头./// </summary>private void CreateSoundFile() {// Open up the wave file for writing.mWaveFile = new FileStream(mFileName, FileMode.Create);mWriter = new BinaryWriter(mWaveFile);/************************************************************************** Here is where the file will be created. A wave file is a RIFF file, which has chunks of data that describe what the file contains. A wave RIFF file is put together like this: The 12 byte RIFF chunk is constructed like this: Bytes 0 - 3 : 'R' 'I' 'F' 'F' Bytes 4 - 7 : Length of file, minus the first 8 bytes of the RIFF description. (4 bytes for "WAVE" + 24 bytes for format chunk length + 8 bytes for data chunk description + actual sample data size.) Bytes 8 - 11: 'W' 'A' 'V' 'E' The 24 byte FORMAT chunk is constructed like this: Bytes 0 - 3 : 'f' 'm' 't' ' ' Bytes 4 - 7 : The format chunk length. This is always 16. Bytes 8 - 9 : File padding. Always 1. Bytes 10- 11: Number of channels. Either 1 for mono, or 2 for stereo. Bytes 12- 15: Sample rate. Bytes 16- 19: Number of bytes per second. Bytes 20- 21: Bytes per sample. 1 for 8 bit mono, 2 for 8 bit stereo or 16 bit mono, 4 for 16 bit stereo. Bytes 22- 23: Number of bits per sample. The DATA chunk is constructed like this: Bytes 0 - 3 : 'd' 'a' 't' 'a' Bytes 4 - 7 : Length of data, in bytes. Bytes 8 -: Actual sample data. ***************************************************************************/// Set up file with RIFF chunk info.char[] ChunkRiff = { 'R', 'I', 'F', 'F' };char[] ChunkType = { 'W', 'A', 'V', 'E' };char[] ChunkFmt = { 'f', 'm', 't', ' ' };char[] ChunkData = { 'd', 'a', 't', 'a' };short shPad = 1; // File paddingint nFormatChunkLength = 0x10; // Format chunk length.int nLength = 0; // File length, minus first 8 bytes of RIFF description. This will be filled in later.short shBytesPerSample = 0; // Bytes per sample.// 一个样本点的字节数目if (8 == mWavFormat.BitsPerSample && 1 == mWavFormat.Channels)shBytesPerSample = 1;else if (( 8 == mWavFormat.BitsPerSample && 2 == mWavFormat.Channels ) || ( 16 == mWavFormat.BitsPerSample && 1 == mWavFormat.Channels ))shBytesPerSample = 2;else if (16 == mWavFormat.BitsPerSample && 2 == mWavFormat.Channels)shBytesPerSample = 4;// RIFF 块mWriter.Write(ChunkRiff);mWriter.Write(nLength);mWriter.Write(ChunkType);// WAVE块mWriter.Write(ChunkFmt);mWriter.Write(nFormatChunkLength);mWriter.Write(shPad);mWriter.Write(mWavFormat.Channels);mWriter.Write(mWavFormat.SamplesPerSecond);mWriter.Write(mWavFormat.AverageBytesPerSecond);mWriter.Write(shBytesPerSample);mWriter.Write(mWavFormat.BitsPerSample);// 数据块mWriter.Write(ChunkData);mWriter.Write((int) 0); // The sample length will be written in later.}#endregion}
}使用这个工具类需要在项目种引入DirecX.dll和DirectX.Sound.dll
java录音
java录音工具类如下
public class EngineeCore {String filePath = "E:\\voice\\voice_cache.wav";AudioFormat audioFormat;TargetDataLine targetDataLine;boolean flag = true;private void stopRecognize() {flag = false;targetDataLine.stop();targetDataLine.close();}private AudioFormat getAudioFormat() {float sampleRate = 16000;// 8000,11025,16000,22050,44100int sampleSizeInBits = 16;// 8,16int channels = 1;// 1,2boolean signed = true;// true,falseboolean bigEndian = false;// true,falsereturn new AudioFormat(sampleRate, sampleSizeInBits, channels, signed, bigEndian);}// end getAudioFormatprivate void startRecognize() {try {// 获得指定的音频格式audioFormat = getAudioFormat();DataLine.Info dataLineInfo = new DataLine.Info(TargetDataLine.class, audioFormat);targetDataLine = (TargetDataLine) AudioSystem.getLine(dataLineInfo);// Create a thread to capture the microphone// data into an audio file and start the// thread running. It will run until the// Stop button is clicked. This method// will return after starting the thread.flag = true;new CaptureThread().start();} catch (Exception e) {e.printStackTrace();} // end catch}// end captureAudio methodclass CaptureThread extends Thread {public void run() {AudioFileFormat.Type fileType = null;File audioFile = new File(filePath);fileType = AudioFileFormat.Type.WAVE;//声音录入的权值int weight = 2;//判断是否停止的计数int downSum = 0;ByteArrayInputStream bais = null;ByteArrayOutputStream baos = new ByteArrayOutputStream();AudioInputStream ais = null;try {targetDataLine.open(audioFormat);targetDataLine.start();byte[] fragment = new byte[1024];ais = new AudioInputStream(targetDataLine);while (flag) {targetDataLine.read(fragment, 0, fragment.length);//当数组末位大于weight时开始存储字节（有声音传入），一旦开始不再需要判断末位if (Math.abs(fragment[fragment.length-1]) > weight || baos.size() > 0) {baos.write(fragment);System.out.println("守卫："+fragment[0]+",末尾："+fragment[fragment.length-1]+",lenght"+fragment.length);//判断语音是否停止if(Math.abs(fragment[fragment.length-1])<=weight){downSum++;}else{System.out.println("重置奇数");downSum=0;}//计数超过20说明此段时间没有声音传入(值也可更改)if(downSum>20){System.out.println("停止录入");break;}}}//取得录音输入流audioFormat = getAudioFormat();byte audioData[] = baos.toByteArray();bais = new ByteArrayInputStream(audioData);ais = new AudioInputStream(bais, audioFormat, audioData.length / audioFormat.getFrameSize());//定义最终保存的文件名System.out.println("开始生成语音文件");AudioSystem.write(ais, AudioFileFormat.Type.WAVE, audioFile);downSum = 0;stopRecognize();} catch (Exception e) {e.printStackTrace();} finally {//关闭流try {ais.close();bais.close();baos.reset();} catch (IOException e) {e.printStackTrace();}}}// end run}// end inner class CaptureThread这个例子实现了多线程录音。支持自动停止
javascript录音
代码如下
/* 音频 */var recorder;var audio = document.querySelector('audio');/* 开始 */function startRecording() {HZRecorder.get(function(rec) {recorder = rec;recorder.start();});}/* 获取数据 */function obtainRecord() {var record = recorder.getBlob();
// debugger;};/* 停止 */function stopRecord() {recorder.stop();};
使用这个来录音需要先下载一个HZRecorder.js。可以在网上下载到
遇到的问题
遇到的问题主要是在识别的过程种因为采样率的问题而无法识别
一定要保持识别的时候的采样率和录音的采样率一致，否则可能会识别失败
这篇关于使用代码录音的三种方案(js,java和C#)的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
