csharp: Sound recording

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using Microsoft.DirectX;
using Microsoft.DirectX.DirectSound;
using System.IO;
using System.Threading;
using System.Data;
using System.Drawing;
using System.Windows.Forms;

namespace AudioBaiduDemo
{

    /// <summary>
    /// DirectSound录音
    /// http://blog.csdn.net/woaixiaozhe/article/details/7852824/
    /// </summary>
    public  class SoundRecorder
    {

        #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
        #endregion

        #region 对外操作函数
        /// <summary>
        /// 构造函数,设定录音设备,设定录音格式.
        /// <summary>
        public SoundRecorder()
        {
            // 初始化音频捕捉设备
            InitCaptureDevice();
            // 设定录音格式
            mWavFormat = CreateWaveFormat();
        }

        /// <summary>
        /// 创建录音格式,此处使用16bit,16KHz,Mono的录音格式
        /// <summary>
        private WaveFormat CreateWaveFormat()
        {
            Microsoft.DirectX.DirectSound.WaveFormat format = new Microsoft.DirectX.DirectSound.WaveFormat();//.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 (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
            Microsoft.DirectX.DirectSound.CaptureBufferDescription bufferdescription = new Microsoft.DirectX.DirectSound.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 padding
            int 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

    }
}

  测试:

    /// <summary>
    ///
    /// </summary>
    public partial class Form4 : Form
    {

        private SoundRecorder recorder = null;    // 录音
        string wavfile = "";
        /// <summary>
        ///
        /// </summary>
        public Form4()
        {
            InitializeComponent();
            recorder = new SoundRecorder();
        }
        /// <summary>
        ///
        /// </summary>
        /// <param name="sender"></param>
        /// <param name="e"></param>
        private void Form4_Load(object sender, EventArgs e)
        {

        }
        /// <summary>
        /// 录音设置
        /// </summary>
        /// <param name="sender"></param>
        /// <param name="e"></param>
        private void button2_Click(object sender, EventArgs e)
        {

            string wavfile = null;
            wavfile = "test.wav";
            recorder.SetFileName(wavfile);
            recorder.RecStart();

        }
        /// <summary>
        /// 停止
        /// </summary>
        /// <param name="sender"></param>
        /// <param name="e"></param>
        private void button3_Click(object sender, EventArgs e)
        {

            recorder.RecStop();
            recorder = null;

        }

  

时间: 2024-10-09 03:41:33

csharp: Sound recording的相关文章

【转帖】Bootleg recording

Bootleg recording From Wikipedia, the free encyclopedia For other uses, see Bootleg (disambiguation). The audio cassette greatly increased the distribution of bootleg recordings in the 1980s. A bootleg recording is an audio or video recording of a pe

How to develop your own Skype call recording software for Windows with Skype desktop API?

Skype is a free voice software, which can point to point with computers for free voice calls, and it charges the low cost with calls directly to the fixed telephone or mobile phone, Skype offers excellent quality and won the favor of many users all o

暴走吧!Snapdragon SDK开发速成指南

(文/Aurora J) Qualcomm的Snapdragon处理器.它快如闪电.效率极高.擅长挑战多任务极限,而且拥有攻城狮们梦寐以求的无限潜能.它能确保您的手机集4G LTE.极速体验.长久续航于一身. Snapdragon处理器不不过CPU. 每一颗Snapdragon处理器都是一个集成了先进专业引擎的精密体系,这些引擎各司其职.协同工作,以超高效率为您带来您所钟爱的移动性能.包含超快的网页浏览速度,不间断的视频和音乐流.以及令人惊叹的3D游戏和拍照等. Snapdragon系列处理器是

alsa 编程

ALSA(Advanced Linux Sound Architecture)是由内核驱动,标准的API库和一系列实用程序组成.因为涉及到版权和BUG的问题Linux 2.6内核抛弃了旧的OSS,ALSA作为声音编程的生力军被作为了合并到了内核中. 数字音频基础: 音频是由电器设备(麦克风等)将空气的变化转化成的电信号.模数转换器(A/D)将模拟电压转化成一系列不连续的值称之为采样,然后将采样值送往数模转化器(D/A)从而将声音还原.采样的频率是影响数字声音质量的一个关键因素,由Nyquist采

ios recepies

当你发现使用cornerRadius不管用时,试试view.layer.masksToBounds = YES;,Read more. 不像在Android下,iOS里面想搞个点击除了button方便点,其他View着实有点麻烦.点击可以这样做,(以UIImageView为例): UITapGestureRecognizer *singleTap = [[UITapGestureRecognizer alloc] initWithTarget:self action:@selector(tapD

How to compare different Skype call recording software on a Windows PC and MAC OSX?

Skype is now the strategy for videoconferencing since first coming on the VoIP landscape more than a decade past, greater furthered with a $8.5-million buyout three years past from the powerful technology large recognized as Ms. It is an excellent pr

csharp:Google TTS API text to speech

? 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86

Csharp: speech to text, text to speech in win

? 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86

【转】Unity3D研究院之通过C#使用Advanced CSharp Messenger(五十)

http://www.xuanyusong.com/archives/2165 Advanced CSharp Messenger 属于C#事件的一种. 维基百科中由详细的说明http://wiki.unity3d.com/index.php?title=Advanced_CSharp_Messenger 上周的一天刚巧有朋友问到我这一块的知识,那么我研究出来将它贴在博客中,帮助了他也帮助我自己!哇咔咔. Advanced CSharp Messenger的特点可以将游戏对象做为参数发送.到底A