Mikel
[转载]关于讯飞语音SDK开发学习 – 或、许 – 博客园.
前奏，浑浑噩噩已经工作一年多，这一年多收获还是挺多的。逛园子应该有两年多了，工作后基本上是天天都会来园子逛逛，园子 里还是有很多牛人写了一些不错的博客，帮我解决很多问题。但是一直没写过博客，归根到底一个字“懒”，还有就是不知道该写 些什么…
今 天把我最近研究讯飞语音东东，分享一下，不过有些还是前辈们提供的。之前公司让我做一个小的语音识别功能，一开始我就建议使用讯飞语音，个人觉得讯飞识别 正确率还是可观的。可是老总说不能考 虑联网，还有就是钱的问题。想到微软自带语音识别引擎（基于win7）。第一次接触到语音识别，没什么头绪，只有收集相关资料 。最后成品出来了，但是识别效果不是那么满意，老总说那就将就用吧，我想他都那样说了，我也没多大意见…开年后老总老总 买了个iphone5玩了siri后，觉得我们现在那个语音太丑陋了，让换一个解决方案，识别率要达到90%。国内有好几家公司做语音识 别的比如科大讯飞、云知声、捷通华声以及紫冬锐意语音都做了一定开放。市面上我知道语音助手有百度语音助手、虫洞语音助手 、360语音助手以及科大讯飞语点；前两个我不知道采用那家公司的还是自己研发的不过都没开开放，360语音助手采用讯飞的。然 后我就继续提议使用讯飞语音SDK，于是乎同事们都下载讯飞语点来玩玩，老总说那就试试讯飞语音SDK。
先 做一个简单demo，看看识别效果，感觉识别率上能够满足要求。一般要的结果不光只是要把所说的话翻译成文字，而是需要的是 语义的理解:例如我要去北京，直接返回北京这个关键。目前讯飞还没把这个接口开放出来，公司负责人说今年会把这个开放出来 。那现在只能使用关键词识别语法，一种是直接是文本词库；另一种是ABNF语法。ABNF写法有点烦杂（语法文件里使用到的词句都是指定的，对于无法枚举 的词句暂时没有很好的解决办法。），就直接采用文本词库（因为关键词有点多）。讯飞还有专门人负责关于讯飞语音问题解答（QQ群：153789256）。
讯飞提供msc.dll这个DLL，调用DLL的封装：
/// <summary>
/// MSCDLL入口封装
/// </summary>
private class MscDll
{
#region MscDLL
/// <summary>
/// 初始化MSC的ISR部分
/// </summary>
/// <param name="configs">初始化时传入的字符串，以指定合成用到的一些配置参数，各个参数以“参数名=参数值”的形式出现，大小写不敏感，不同的参数之间以“,”或“\n”隔开，不设置任何值时可以传入NULL或空串：</param>
/// <returns>如果函数调用成功返回MSP_SUCCESS，否则返回错误代码，错误代码参见msp_errors</returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern int QISRInit(string configs);
/// <summary>
/// 开始一个ISR会话
/// </summary>
/// <param name="grammarList">uri-list格式的语法，可以是一个语法文件的URL或者一个引擎内置语法列表。可以同时指定多个语法，不同的语法之间以“,”
/// 隔开。进行语音听写时不需要语法，此参数设定为NULL或空串即可；进行语音识别时则需要语法，语法可以在此参数中指定，也可以随后调用QISRGrammarActivate指定识别所用的语法。</param>
/// <param name="_params">本路ISR会话使用的参数，可设置的参数及其取值范围请参考《可设置参数列表_MSP20.xls》，各个参数以“参数名=参数值” 的形式出现，不同的参数之间以“,”或者“\n”隔开。</param>
/// <param name="errorCode">如果函数调用成功则其值为MSP_SUCCESS，否则返回错误代码，错误代码参见msp_errors。几个主要的返回值： MSP_ERROR_NOT_INIT 未初始化 MSP_ERROR_INVALID_PARA 无效的参数; MSP_ERROR_NO_LICENSE 开始一路会话失败</param>
/// <returns>MSC为本路会话建立的ID，用来唯一的标识本路会话，供以后调用其他函数时使用。函数调用失败则会返回NULL。</returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern IntPtr QISRSessionBegin(string grammarList, string _params, ref int errorCode);
/// <summary>
/// 传入语法
/// </summary>
/// <param name="sessionID">由QISRSessionBegin返回过来的会话ID</param>
/// <param name="grammar">语法字符串</param>
/// <param name="type">语法类型，可以是uri-list、abnf、xml等</param>
/// <param name="weight">本次传入语法的权重，本参数在MSP 2.0中会被忽略。</param>
/// <returns>如果函数调用成功返回MSP_SUCCESS，否则返回错误代码，错误代码参见msp_errors</returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern int QISRGrammarActivate(string sessionID, string grammar, string type, int weight);
/// <summary>
/// 写入用来识别的语音
/// </summary>
/// <param name="sessionID">由QISRSessionBegin返回过来的会话ID</param>
/// <param name="waveData">音频数据缓冲区起始地址</param>
/// <param name="waveLen">音频数据长度，其大小不能超过设定的max_audio_size</param>
/// <param name="audioStatus">用来指明用户本次识别的音频是否发送完毕，可能值如下：
/// MSP_AUDIO_SAMPLE_FIRST = 1 第一块音频
/// MSP_AUDIO_SAMPLE_CONTINUE = 2 还有后继音频
/// MSP_AUDIO_SAMPLE_LAST = 4 最后一块音频</param>
/// <param name="epStatus">端点检测（End-point detected）器所处的状态，可能的值如下:
/// MSP _EP_LOOKING_FOR_SPEECH = 0 还没有检测到音频的前端点。
/// MSP _EP_IN_SPEECH = 1 已经检测到了音频前端点，正在进行正常的音频处理。
/// MSP _EP_AFTER_SPEECH = 3 检测到音频的后端点，后继的音频会被MSC忽略。
/// MSP _EP_TIMEOUT = 4 超时。
/// MSP _EP_ERROR= 5 出现错误。
/// MSP _EP_MAX_SPEECH = 6 音频过大。</param>
/// <param name="recogStatus">识别器所处的状态</param>
/// <returns></returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern int QISRAudioWrite(string sessionID, byte[] waveData, uint waveLen, AudioStatus audioStatus, ref EpStatus epStatus, ref RecogStatus recogStatus);
/// <summary>
/// 获取识别结果
/// </summary>
/// <param name="sessionID">由QISRSessionBegin返回过来的会话ID</param>
/// <param name="rsltStatus">识别结果的状态，其取值范围和含义请参考QISRAudioWrite的参数recogStatus</param>
/// <param name="waitTime">与服务器交互的间隔时间，可以控制和服务器的交互频度。单位为ms，建议取值为5000</param>
/// <param name="errorCode">如果函数调用成功返回MSP_SUCCESS，否则返回错误代码，错误代码参见msp_errors</param>
/// <returns>函数执行成功并且获取到识别结果时返回识别结果，函数执行成功没有获取到识别结果时返回NULL</returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern IntPtr QISRGetResult(string sessionID, ref RecogStatus rsltStatus, int waitTime, ref int errorCode);
/// <summary>
/// 结束一路会话
/// </summary>
/// <param name="sessionID">由QISRSessionBegin返回过来的会话ID</param>
/// <param name="hints">结束本次会话的原因描述，用于记录日志，便于用户查阅或者跟踪某些问题</param>
/// <returns></returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern int QISRSessionEnd(string sessionID, string hints);
/// <summary>
/// 获取与识别交互相关的参数
/// </summary>
/// <param name="sessionID">由QISRSessionBegin返回过来的会话ID</param>
/// <param name="paramName">要获取的参数名称；支持同时查询多个参数，查询多个参数时，参数名称按“,” 或“\n”分隔开来</param>
/// <param name="paramValue">获取的参数值，以字符串形式返回；查询多个参数时，参数值之间以“;”分开，不支持的参数将返回空的值</param>
/// <param name="valueLen">参数值的长度</param>
/// <returns></returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern int QISRGetParam(string sessionID, string paramName, string paramValue, ref uint valueLen);
/// <summary>
/// 逆初始化MSC的ISR部分
/// </summary>
/// <returns></returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern int QISRFini();
/// <summary>
/// 上传用户自定义词库
/// </summary>
/// <param name="sessionID">由QISRSessionBegin返回过来的会话ID</param>
/// <param name="dataName">词库名称</param>
/// <param name="userData">词库数据采用是utf8格式</param>
/// <param name="lenght">词库大小</param>
/// <param name="paramValue">参数值</param>
/// <param name="errorCode">如果函数调用成功返回MSP_SUCCESS，否则返回错误代码，错误代码参见msp_errors</param>
/// <returns>函数执行成功并且返回exID（词库编号)</returns>
[DllImport("msc.dll", CallingConvention = CallingConvention.StdCall)]
public static extern IntPtr QISRUploadData(string sessionID, string dataName, byte[] userData, uint lenght, string paramValue, ref int errorCode);
#endregion
}
说明一下：“QISRUploadData”（上传词库）这个函数在开发文档里面没的，讯飞遗漏了。
具体实现(关键词识别，文本词库)：
类：MscNet
#region 定义字段
//返回错误代号
private int ret = 0;
private RecoErrors Re = null;
/// <summary>
/// 会话ID
/// </summary>
private string sess_id = null;
/// <summary>
/// 参数
/// </summary>
private string param = null;
/// <summary>
/// 语法
/// </summary>
private string grammar = null;
//错误消息通知托管
public delegate void delegdateOnerror(string Msg);
private string path = null;
/// <summary>
/// 识别数据返回的事件
/// </summary>
public event EventHandler<DataArrivedEventArgs> DataArrived;
/// <summary>
/// 识别过程结束的事件
/// </summary>
public event EventHandler ISREnd;
/// <summary>
/// 正在识别
/// </summary>
public event EventHandler Spoting;
#endregion
#region 构造函数
/// <summary>
/// 构造函数，初始化引擎
/// </summary>
/// <param name="appid">appid</param>
/// <param name="param">参数</param>
/// <param name="grammar">语法ID</param>
/// <param name="path">路径</param>
public MscNet(string appid, string param, string path, string grammar)
{
this.path = path;
this.param = param;
this.grammar = grammar;
Re = new RecoErrors();
//引擎初始化，只需初始化一次
ret = MscDll.QISRInit("appid=" + appid);
try
{
Re.GetError(ret);
}
catch (MscException ex)
{
RaiseError(ex.Message.ToString());
}
}
#endregion
#region 公共方法
/// <summary>
/// 开始识别语音
/// </summary>
/// <param name="buffer">音频数据</param>
public void InterpretVoice(byte[] buffer)
{
//用来指明用户本次识别的音频是否发送完毕
AudioStatus audioStatus = AudioStatus.ISR_AUDIO_SAMPLE_LAST;
//端点检测（End-point detected）器所处的状态
EpStatus ep_status = EpStatus.ISR_EP_NULL;
//识别器所处的状态
RecogStatus rec_status = RecogStatus.ISR_REC_NULL;
//识别结果的状态
RecogStatus rslt_status = RecogStatus.ISR_REC_NULL;
Loadgrammar();
int ret = MscDll.QISRAudioWrite(sess_id, buffer, (uint)buffer.Length, audioStatus, ref ep_status, ref rec_status);
try
{
Re.GetError(ret);
do
{
if (rslt_status == RecogStatus.ISR_REC_STATUS_INCOMPLETE)
{
Spoting(this, new EventArgs());//通知正在识别
}
IntPtr p = MscDll.QISRGetResult(sess_id, ref rslt_status, 0, ref ret);
Re.GetError(ret);
if (p != IntPtr.Zero)
{
string tmp = PtrToStr(p);
DataArrived(this, new DataArrivedEventArgs(tmp));//激发识别数据到达事件
}
System.Threading.Thread.Sleep(500);
} while (rslt_status != RecogStatus.ISR_REC_STATUS_SPEECH_COMPLETE);
}
catch (MscException ex)
{
RaiseError(ex.Message);
}
finally
{
try
{
ret = MscDll.QISRSessionEnd(sess_id, string.Empty);
Re.GetError(ret);
ISREnd(this, new EventArgs());//通知识别结束
}
catch (MscException ex)
{
RaiseError(ex.Message);
}
}
}
/// <summary>
/// 上传词库词库采用是utf8格式
/// </summary>
/// <param name="txtFile">词库名称</param>
/// <param name="path">词库路径</param>
/// <param name="param">参数</param>
/// <returns>返回词库编号</returns>
public string GetExID(string txtFile, string path, string param)
{
string filePath = Path.Combine(path, txtFile);
string tmp = string.Empty;
if (!string.IsNullOrEmpty(filePath))
{
try
{
sess_id = PtrToStr(MscDll.QISRSessionBegin(null, param, ref ret));
Re.GetError(ret);
try
{
using (FileStream fs = File.Open(filePath, FileMode.Open))
{
long len = fs.Length;
byte[] buffer = new byte[len];
fs.Read(buffer, 0, (int)len);
IntPtr p = MscDll.QISRUploadData(sess_id, "sces", buffer, (uint)fs.Length, "dtt=keylist", ref ret);
Re.GetError(ret);
if (p != IntPtr.Zero)
{
tmp = PtrToStr(p);
}
}
}
catch (FileNotFoundException ex)
{
RaiseError(ex.Message);
}
}
catch (MscException ex)
{
RaiseError(ex.Message);
}
finally
{
try
{
ret = MscDll.QISRSessionEnd(sess_id, null);
Re.GetError(ret);
}
catch (MscException ex)
{
RaiseError(ex.Message.ToString());
}
}
}
else
{
RaiseError("路径不正确！");
}
return tmp;
}
/// <summary>
/// 对MSC的ISR部分进行逆初始化。
/// </summary>
public void QISRFini()
{
try
{
ret = MscDll.QISRFini();
Re.GetError(ret);
}
catch (MscException ex)
{
RaiseError(ex.Message.ToString());
}
}
#endregion
#region 受保护方法
/// <summary>
/// 加载语法
/// </summary>
private void Loadgrammar()
{
try
{
sess_id = PtrToStr(MscDll.QISRSessionBegin(grammar, param, ref ret));
Re.GetError(ret);
}
catch (MscException ex)
{
RaiseError(ex.Message);
}
}
/// <summary>
/// 指针转字符串
/// </summary>
/// <param name="p">指向非托管代码字符串的指针</param>
/// <returns>返回指针指向的字符串</returns>
private string PtrToStr(IntPtr p)
{
List<byte> lb = new List<byte>();
try
{
while (Marshal.ReadByte(p) != 0)
{
lb.Add(Marshal.ReadByte(p));
p = p + 1;
}
}
catch (AccessViolationException ex)
{
RaiseError(ex.Message);
}
return Encoding.Default.GetString(lb.ToArray());
}
#endregion
#region 事件
/// <summary>
/// 错误通知事件
/// </summary>
public event delegdateOnerror OnError;
private void RaiseError(string Msg)
{
if (OnError != null)
{
OnError(Msg);
}
}
/// <summary>
/// 有识别数据返回的事件参数，包含了识别的文本结果
/// </summary>
public class DataArrivedEventArgs : EventArgs
{
public string result;
public DataArrivedEventArgs(string rs)
{
result = rs;
}
}
#endregion
如果采用ABNF语法，只是与文本词库加载语法方式有点不一样：
/// <summary>
/// 加载语法
/// </summary>
private void Loadgrammar()
{
try
{
//sess_id = PtrToStr(MscDll.QISRSessionBegin(grammar, param, ref ret));
/*ABNF语法*/
sess_id = PtrToStr(MscDll.QISRSessionBegin(null, "rst=plain,sub=asr,ssm=1,aue=speex,auf=audio/L16;rate=16000,cfd=350", ref ret));
em.GetError(ret);
string grammar1 = "#ABNF 1.0 GB2312;\n mode voice;\n language zh-cn;\n\n\n root $main;\n public $main = 我[想要]看$place1;\n $place1=足球;\n";
ret = MscDll.QISRGrammarActivate(sess_id, grammar1, "abnf", 0);//将语法ID传入QISRSessionBegin
/*end */
em.GetError(ret);
}
catch (MscException ex)
{
RaiseError(ex.Message.ToString());
}
}
常量的枚举：
#region 错误代号
enum ErrorCode
{
MSP_SUCCESS= 0,
MSP_ERROR_FAIL = -1,
MSP_ERROR_EXCEPTION = -2,
/* General errors 10100(0x2774) */
MSP_ERROR_GENERAL = 10100, /* 0x2774 */
MSP_ERROR_OUT_OF_MEMORY = 10101, /* 0x2775 */
MSP_ERROR_FILE_NOT_FOUND = 10102, /* 0x2776 */
MSP_ERROR_NOT_SUPPORT = 10103, /* 0x2777 */
MSP_ERROR_NOT_IMPLEMENT = 10104, /* 0x2778 */
MSP_ERROR_ACCESS = 10105, /* 0x2779 */
MSP_ERROR_INVALID_PARA = 10106, /* 0x277A */
MSP_ERROR_INVALID_PARA_VALUE = 10107, /* 0x277B */
MSP_ERROR_INVALID_HANDLE = 10108, /* 0x277C */
MSP_ERROR_INVALID_DATA = 10109, /* 0x277D */
MSP_ERROR_NO_LICENSE = 10110, /* 0x277E */
MSP_ERROR_NOT_INIT = 10111, /* 0x277F */
MSP_ERROR_NULL_HANDLE = 10112, /* 0x2780 */
MSP_ERROR_OVERFLOW = 10113, /* 0x2781 */
MSP_ERROR_TIME_OUT = 10114, /* 0x2782 */
MSP_ERROR_OPEN_FILE = 10115, /* 0x2783 */
MSP_ERROR_NOT_FOUND = 10116, /* 0x2784 */
MSP_ERROR_NO_ENOUGH_BUFFER = 10117, /* 0x2785 */
MSP_ERROR_NO_DATA = 10118, /* 0x2786 */
MSP_ERROR_NO_MORE_DATA = 10119, /* 0x2787 */
MSP_ERROR_SKIPPED = 10120, /* 0x2788 */
MSP_ERROR_ALREADY_EXIST = 10121, /* 0x2789 */
MSP_ERROR_LOAD_MODULE = 10122, /* 0x278A */
MSP_ERROR_BUSY = 10123, /* 0x278B */
MSP_ERROR_INVALID_CONFIG = 10124, /* 0x278C */
MSP_ERROR_VERSION_CHECK = 10125, /* 0x278D */
MSP_ERROR_CANCELED = 10126, /* 0x278E */
MSP_ERROR_INVALID_MEDIA_TYPE = 10127, /* 0x278F */
MSP_ERROR_CONFIG_INITIALIZE = 10128, /* 0x2790 */
MSP_ERROR_CREATE_HANDLE = 10129, /* 0x2791 */
MSP_ERROR_CODING_LIB_NOT_LOAD = 10130, /* 0x2792 */
/* Error codes of network 10200(0x27D8)*/
MSP_ERROR_NET_GENERAL = 10200, /* 0x27D8 */
MSP_ERROR_NET_OPENSOCK = 10201, /* 0x27D9 */ /* Open socket */
MSP_ERROR_NET_CONNECTSOCK = 10202, /* 0x27DA */ /* Connect socket */
MSP_ERROR_NET_ACCEPTSOCK = 10203, /* 0x27DB */ /* Accept socket */
MSP_ERROR_NET_SENDSOCK = 10204, /* 0x27DC */ /* Send socket data */
MSP_ERROR_NET_RECVSOCK = 10205, /* 0x27DD */ /* Recv socket data */
MSP_ERROR_NET_INVALIDSOCK = 10206, /* 0x27DE */ /* Invalid socket handle */
MSP_ERROR_NET_BADADDRESS = 10207, /* 0x27EF */ /* Bad network address */
MSP_ERROR_NET_BINDSEQUENCE = 10208, /* 0x27E0 */ /* Bind after listen/connect */
MSP_ERROR_NET_NOTOPENSOCK = 10209, /* 0x27E1 */ /* Socket is not opened */
MSP_ERROR_NET_NOTBIND = 10210, /* 0x27E2 */ /* Socket is not bind to an address */
MSP_ERROR_NET_NOTLISTEN = 10211, /* 0x27E3 */ /* Socket is not listenning */
MSP_ERROR_NET_CONNECTCLOSE = 10212, /* 0x27E4 */ /* The other side of connection is closed */
MSP_ERROR_NET_NOTDGRAMSOCK = 10213, /* 0x27E5 */ /* The socket is not datagram type */
MSP_ERROR_NET_DNS=10214,
/* Error codes of mssp message 10300(0x283C) */
MSP_ERROR_MSG_GENERAL = 10300, /* 0x283C */
MSP_ERROR_MSG_PARSE_ERROR = 10301, /* 0x283D */
MSP_ERROR_MSG_BUILD_ERROR = 10302, /* 0x283E */
MSP_ERROR_MSG_PARAM_ERROR = 10303, /* 0x283F */
MSP_ERROR_MSG_CONTENT_EMPTY = 10304, /* 0x2840 */
MSP_ERROR_MSG_INVALID_CONTENT_TYPE = 10305, /* 0x2841 */
MSP_ERROR_MSG_INVALID_CONTENT_LENGTH = 10306, /* 0x2842 */
MSP_ERROR_MSG_INVALID_CONTENT_ENCODE = 10307, /* 0x2843 */
MSP_ERROR_MSG_INVALID_KEY = 10308, /* 0x2844 */
MSP_ERROR_MSG_KEY_EMPTY = 10309, /* 0x2845 */
MSP_ERROR_MSG_SESSION_ID_EMPTY = 10310, /* 0x2846 */
MSP_ERROR_MSG_LOGIN_ID_EMPTY = 10311, /* 0x2847 */
MSP_ERROR_MSG_SYNC_ID_EMPTY = 10312, /* 0x2848 */
MSP_ERROR_MSG_APP_ID_EMPTY = 10313, /* 0x2849 */
MSP_ERROR_MSG_EXTERN_ID_EMPTY = 10314, /* 0x284A */
MSP_ERROR_MSG_INVALID_CMD = 10315, /* 0x284B */
MSP_ERROR_MSG_INVALID_SUBJECT = 10316, /* 0x284C */
MSP_ERROR_MSG_INVALID_VERSION = 10317, /* 0x284D */
MSP_ERROR_MSG_NO_CMD = 10318, /* 0x284E */
MSP_ERROR_MSG_NO_SUBJECT = 10319, /* 0x284F */
MSP_ERROR_MSG_NO_VERSION = 10320, /* 0x2850 */
MSP_ERROR_MSG_MSSP_EMPTY = 10321, /* 0x2851 */
MSP_ERROR_MSG_NEW_RESPONSE = 10322, /* 0x2852 */
MSP_ERROR_MSG_NEW_CONTENT = 10323, /* 0x2853 */
MSP_ERROR_MSG_INVALID_SESSION_ID = 10324, /* 0x2854 */
/* Error codes of DataBase 10400(0x28A0)*/
MSP_ERROR_DB_GENERAL = 10400, /* 0x28A0 */
MSP_ERROR_DB_EXCEPTION = 10401, /* 0x28A1 */
MSP_ERROR_DB_NO_RESULT = 10402, /* 0x28A2 */
MSP_ERROR_DB_INVALID_USER = 10403, /* 0x28A3 */
MSP_ERROR_DB_INVALID_PWD = 10404, /* 0x28A4 */
MSP_ERROR_DB_CONNECT = 10405, /* 0x28A5 */
MSP_ERROR_DB_INVALID_SQL = 10406, /* 0x28A6 */
MSP_ERROR_DB_INVALID_APPID = 10407, /* 0x28A7 */
/* Error codes of Resource 10500(0x2904)*/
MSP_ERROR_RES_GENERAL = 10500, /* 0x2904 */
MSP_ERROR_RES_LOAD = 10501, /* 0x2905 */ /* Load resource */
MSP_ERROR_RES_FREE = 10502, /* 0x2906 */ /* Free resource */
MSP_ERROR_RES_MISSING = 10503, /* 0x2907 */ /* Resource File Missing */
MSP_ERROR_RES_INVALID_NAME = 10504, /* 0x2908 */ /* Invalid resource file name */
MSP_ERROR_RES_INVALID_ID = 10505, /* 0x2909 */ /* Invalid resource ID */
MSP_ERROR_RES_INVALID_IMG = 10506, /* 0x290A */ /* Invalid resource image pointer */
MSP_ERROR_RES_WRITE = 10507, /* 0x290B */ /* Write read-only resource */
MSP_ERROR_RES_LEAK = 10508, /* 0x290C */ /* Resource leak out */
MSP_ERROR_RES_HEAD = 10509, /* 0x290D */ /* Resource head currupt */
MSP_ERROR_RES_DATA = 10510, /* 0x290E */ /* Resource data currupt */
MSP_ERROR_RES_SKIP = 10511, /* 0x290F */ /* Resource file skipped */
/* Error codes of TTS 10600(0x2968)*/
MSP_ERROR_TTS_GENERAL = 10600, /* 0x2968 */
MSP_ERROR_TTS_TEXTEND = 10601, /* 0x2969 */ /* Meet text end */
MSP_ERROR_TTS_TEXT_EMPTY = 10602, /* 0x296A */ /* no synth text */
/* Error codes of Recognizer 10700(0x29CC) */
MSP_ERROR_REC_GENERAL = 10700, /* 0x29CC */
MSP_ERROR_REC_INACTIVE = 10701, /* 0x29CD */
MSP_ERROR_REC_GRAMMAR_ERROR = 10702, /* 0x29CE */
MSP_ERROR_REC_NO_ACTIVE_GRAMMARS = 10703, /* 0x29CF */
MSP_ERROR_REC_DUPLICATE_GRAMMAR = 10704, /* 0x29D0 */
MSP_ERROR_REC_INVALID_MEDIA_TYPE = 10705, /* 0x29D1 */
MSP_ERROR_REC_INVALID_LANGUAGE = 10706, /* 0x29D2 */
MSP_ERROR_REC_URI_NOT_FOUND = 10707, /* 0x29D3 */
MSP_ERROR_REC_URI_TIMEOUT = 10708, /* 0x29D4 */
MSP_ERROR_REC_URI_FETCH_ERROR = 10709, /* 0x29D5 */
/* Error codes of Speech Detector 10800(0x2A30) */
MSP_ERROR_EP_GENERAL = 10800, /* 0x2A30 */
MSP_ERROR_EP_NO_SESSION_NAME = 10801, /* 0x2A31 */
MSP_ERROR_EP_INACTIVE = 10802, /* 0x2A32 */
MSP_ERROR_EP_INITIALIZED = 10803, /* 0x2A33 */
/* Error codes of TUV */
MSP_ERROR_TUV_GENERAL = 10900, /* 0x2A94 */
MSP_ERROR_TUV_GETHIDPARAM = 10901, /* 0x2A95 */ /* Get Busin Param huanid*/
MSP_ERROR_TUV_TOKEN = 10902, /* 0x2A96 */ /* Get Token */
MSP_ERROR_TUV_CFGFILE = 10903, /* 0x2A97 */ /* Open cfg file */
MSP_ERROR_TUV_RECV_CONTENT = 10904, /* 0x2A98 */ /* received content is error */
MSP_ERROR_TUV_VERFAIL = 10905, /* 0x2A99 */ /* Verify failure */
/* Error codes of IMTV */
MSP_ERROR_IMTV_SUCCESS = 11000, /* 0x2AF8 */ /* 成功 */
MSP_ERROR_IMTV_NO_LICENSE = 11001, /* 0x2AF9 */ /* 试用次数结束，用户需要付费 */
MSP_ERROR_IMTV_SESSIONID_INVALID = 11002, /* 0x2AFA */ /* SessionId失效，需要重新登录通行证 */
MSP_ERROR_IMTV_SESSIONID_ERROR = 11003, /* 0x2AFB */ /* SessionId为空，或者非法 */
MSP_ERROR_IMTV_UNLOGIN = 11004, /* 0x2AFC */ /* 未登录通行证 */
MSP_ERROR_IMTV_SYSTEM_ERROR = 11005, /* 0x2AFD */ /* 系统错误 */
/* Error codes of HCR */
MSP_ERROR_HCR_GENERAL = 11100,
MSP_ERROR_HCR_RESOURCE_NOT_EXIST = 11101,
/* Error codes of http 12000(0x2EE0) */
MSP_ERROR_HTTP_BASE = 12000, /* 0x2EE0 */
/*Error codes of ISV */
MSP_ERROR_ISV_NO_USER = 13000, /* 32C8 */ /* the user doesn't exist */
}
#endregion
#region ISR枚举常量
public enum AudioStatus
{
ISR_AUDIO_SAMPLE_INIT = 0x00,
ISR_AUDIO_SAMPLE_FIRST = 0x01,
ISR_AUDIO_SAMPLE_CONTINUE = 0x02,
ISR_AUDIO_SAMPLE_LAST = 0x04,
ISR_AUDIO_SAMPLE_SUPPRESSED = 0x08,
ISR_AUDIO_SAMPLE_LOST = 0x10,
ISR_AUDIO_SAMPLE_NEW_CHUNK = 0x20,
ISR_AUDIO_SAMPLE_END_CHUNK = 0x40,
ISR_AUDIO_SAMPLE_VALIDBITS = 0x7f /* to validate the value of sample->status */
}
public enum EpStatus
{
ISR_EP_NULL = -1,
ISR_EP_LOOKING_FOR_SPEECH = 0, ///还没有检测到音频的前端点
ISR_EP_IN_SPEECH = 1, ///已经检测到了音频前端点，正在进行正常的音频处理。
ISR_EP_AFTER_SPEECH = 3, ///检测到音频的后端点，后继的音频会被MSC忽略。
ISR_EP_TIMEOUT = 4, ///超时
ISR_EP_ERROR = 5, ///出现错误
ISR_EP_MAX_SPEECH = 6 ///音频过大
}
public enum RecogStatus
{
ISR_REC_NULL = -1,
ISR_REC_STATUS_SUCCESS = 0, ///识别成功，此时用户可以调用QISRGetResult来获取（部分）结果。
ISR_REC_STATUS_NO_MATCH = 1, ///识别结束，没有识别结果
ISR_REC_STATUS_INCOMPLETE = 2, ///正在识别中
ISR_REC_STATUS_NON_SPEECH_DETECTED = 3, ///保留
ISR_REC_STATUS_SPEECH_DETECTED = 4, ///发现有效音频
ISR_REC_STATUS_SPEECH_COMPLETE = 5, ///识别结束
ISR_REC_STATUS_MAX_CPU_TIME = 6, ///保留
ISR_REC_STATUS_MAX_SPEECH = 7, ///保留
ISR_REC_STATUS_STOPPED = 8, ///保留
ISR_REC_STATUS_REJECTED = 9, ///保留
ISR_REC_STATUS_NO_SPEECH_FOUND = 10 ///没有发现音频
}
#endregion
}
自定义异常：
[Serializable] //声明为可序列化的 因为要写入文件中
public class MscException : ApplicationException//由用户程序引发，用于派生自定义的异常类型
{
/// <summary>
/// 默认构造函数
/// </summary>
public MscException() { }
public MscException(string message)
: base(message) { }
public MscException(string message, Exception inner)
: base(message, inner) { }
}
/// <summary>
/// 是否出错
/// </summary>
internal class RecoErrors
{
public RecoErrors() { }
/// <summary>
/// 是否发生错误.
/// </summary>
/// <param name="id">错误ID</param>
public virtual void GetError(int id)
{
if (id != 0)
{
var ex = new MscException(((ErrorCode)id).ToString("G"));
// var ex = new MscException(Enum.GetName(typeof(ErrorCode),id));
throw ex;
}
}
}
讯飞语音支持边录边上传，不过我这里采用是一次性上传。起初我采用的是边录边上传，不过感觉有数字混合后识别正常率不好（还没跟讯飞那边沟通。），最后才使用一次性上传，毕竟语音文件也不是大就200KB一下。讯飞语音识别不支持多线程识别。
我做的这个语音识别产品，做成服务端与客户端。服务端：放在一个能连接外网机子上提供语音识别（做了一个简单队列），客户端：将音频数据采集后发送到局域网内的语音识别服务端进行识别。
以上有些代码是借助别人的，第一次写大家尽量不要吐槽，不过可以给点意见。大家相互学习…
