/** @function
********************************************************************************
<PRE>
函数名: JudgeTrainFrame2()
功能: 判断预增强后的数据是否可以作为训练帧（去除静寂语音的多段连接起来）
用法:
参数:
[IN] pDiffVoice: 增强（差分）后的语音数据
[IN] iSampleNum: 语音样本数
[IN] train_frame_num: 训练帧帧数
返回:
非空: 可以作为训练帧的信号首地址
NULL: 不可作为训练帧
调用: HalfFrameEnergy()
主调函数: voiceToMFCC()
备注: 返回的内存需要用户在voiceToMFCC()中自行释放
</PRE>
*******************************************************************************/
static double * JudgeTrainFrame2(double * pDiffVoice, int iSampleNum, int train_frame_num)
{
int len = 0;
int iNum; // 合格的语音帧数
int iFrame; // 帧序号
int iFrameNum = (iSampleNum>>7) - 1; // 帧总数=2*(样本数/256)-1
double PriorHalfFrame = 0; // 前半帧能量(前128B)
double NextHalfFrame = 0; // 后半帧能量(后128B)
double FrameEnergy = 0; // 一帧的累积能量
double * pTranDiff = NULL; // 合格语音
double * pSave; // 合格语音存储地址
double * pDiffHead = pDiffVoice;
double * pDiffNext = pDiffVoice;
if (iFrameNum < train_frame_num)
{
return NULL;
}
pTranDiff = (double *)calloc((train_frame_num/2 + 1) * FRAME_LEN, sizeof(double));
if (!pTranDiff)
{
return NULL;
}
pSave = pTranDiff;
PriorHalfFrame = HalfFrameEnergy(pDiffHead);
for (iFrame=1, iNum=0; iFrame<iFrameNum && iNum<train_frame_num; ++iFrame)
{
pDiffNext += (FRAME_LEN/2); // 指向iFrame号帧的后半帧
NextHalfFrame = HalfFrameEnergy(pDiffNext);
FrameEnergy = PriorHalfFrame + NextHalfFrame;
if (FrameEnergy < SILENCE_VALUE) // 是静寂语音
{
if (iFrameNum-iFrame < train_frame_num-iNum) // 剩下的帧不足以作为训练帧
{
free(pTranDiff);
return NULL;
}
len = (int)(pDiffNext - pDiffHead - FRAME_LEN/2);
if (len > 0)
{
memcpy(pSave, pDiffHead, len * sizeof(double));
pSave += len;
}
pDiffNext += FRAME_LEN/2; // 重新定位可用作训练的帧
pDiffHead= pDiffNext;
NextHalfFrame = HalfFrameEnergy(pDiffHead);
++iFrame;
}
else
{
++iNum;
}
PriorHalfFrame = NextHalfFrame;
} // end: for(;;)
len = (int)(pDiffNext - pDiffHead + FRAME_LEN/2);
if (len > 0)
{
memcpy(pSave, pDiffHead, len * sizeof(double));
}
return pTranDiff;
}
/** @function
********************************************************************************
<PRE>
函数名: JudgeTrainFrame2()
功能: 判断预增强后的数据是否可以作为训练帧（去除静寂语音的多段连接起来）
用法:
参数:
[IN] pDiffVoice: 增强（差分）后的语音数据
[IN] iSampleNum: 语音样本数
返回:
非空: 可以作为训练帧的信号首地址
NULL: 不可作为训练帧
调用: HalfFrameEnergy()
主调函数: voiceToMFCC()
备注: 返回的内存需要用户在voiceToMFCC()中自行释放
</PRE>
*******************************************************************************/
static double * JudgeTrainFrame2(double * pDiffVoice, int iSampleNum)
{
int len = 0;
int iNum; //合格的语音帧数
int iFrame; //帧序号
int iFrameNum = (iSampleNum>>7) - 1; //帧总数=2*(样本数/256)-1
double PrHalfFrame = 0; //前半帧能量(前128B)
double NextHalfFrame = 0; //后半帧能量(后128B)
double FrameEnergy = 0; //一帧的累积能量
double * pTranDiff = NULL; //合格语音
double * pSave; //合格语音存储地址
double * pDiffHead = pDiffVoice;
double * pDiffNext = pDiffVoice;
pTranDiff = (double *)calloc((GOOD_FRAME_NUM / 2 + 1)*FRAME_LEN, sizeof(double));
if (!pTranDiff)
{
return NULL;
}
//pTranDiff = (double *)malloc((GOOD_FRAME_NUM/2 + 1)*sizeof(double));
pSave = pTranDiff;
PrHalfFrame = HalfFrameEnergy(pDiffHead);
for (iFrame=1,iNum=0; iFrame<iFrameNum && iNum<GOOD_FRAME_NUM; ++iFrame)
{
// 指针的加减法是按步长来算
pDiffNext += FRAME_LEN / 2; // 指针后移128
NextHalfFrame = HalfFrameEnergy(pDiffNext);
FrameEnergy = PrHalfFrame + NextHalfFrame;
if (FrameEnergy < SILENCE_VALUE) // 是静寂语音
{
if (iFrameNum-iFrame < GOOD_FRAME_NUM-iNum) // 剩下的帧不足以作为训练帧
{
free(pTranDiff);
return NULL;
}
len = pDiffNext - pDiffHead - FRAME_LEN / 2;
if (len > 0)
{
memcpy(pSave, pDiffHead, len * sizeof(double));
pSave += len;
}
pDiffHead = pDiffNext + FRAME_LEN / 2; // 重新定位可用作训练的帧
pDiffNext = pDiffHead;
NextHalfFrame = HalfFrameEnergy(pDiffHead);
}
else
{
++iNum;
}
PrHalfFrame = NextHalfFrame;
}
len = pDiffNext - pDiffHead + FRAME_LEN / 2;
if (len > 0)
{
//TODO 把分配的内存损坏了
memcpy(pSave, pDiffHead, len * sizeof(double));
}
return pTranDiff;
}
