这可能是不言而喻的，但我认为如果你对 C 作为一种语言没有很好的处理能力，你会发现很难使用 SAPI 的 C 接口。我写了一个程序，几乎完全按照你前段时间所说的来测试这个概念。首先是代码转储：
#include "dirent.h"
#include <iostream>
#include <string>
#include <sapi.h>
#include <sphelper.h>
int main(int argc, char* argv[]){
DIR *dir;
struct dirent* entry;
struct stat* statbuf;
::CoInitialize(NULL);
if((dir = opendir(".")) != NULL){
while((entry = readdir(dir)) != NULL){
char extCheck[260];
strcpy(extCheck, entry->d_name);
if(strlen(extCheck) > 4 && !strcmp(strlwr(extCheck) + strlen(extCheck)-4, ".wav")){
//printf("%s\n",entry->d_name);
//1. Find the wav files
//2. Check the wavs to make sure they're the correct format
//3. Output any errors to the error log
//4. Produce the text files for the wavs
//5. Cleanup and exit
FILE* fp;
std::string fileName = std::string(entry->d_name,entry->d_name + strlen(entry->d_name)-4);
fileName += ".txt";
fp = fopen(fileName.c_str(), "w+");
HRESULT hr = S_OK;
CComPtr<ISpStream> cpInputStream;
CComPtr<ISpRecognizer> cpRecognizer;
CComPtr<ISpRecoContext> cpRecoContext;
CComPtr<ISpRecoGrammar> cpRecoGrammar;
CSpStreamFormat sInputFormat;
hr = cpRecognizer.CoCreateInstance(CLSID_SpInprocRecognizer);
hr = cpInputStream.CoCreateInstance(CLSID_SpStream);
hr = sInputFormat.AssignFormat(SPSF_16kHz16BitStereo);
std::string sInputFileName = entry->d_name;
std::wstring wInputFileName = std::wstring(sInputFileName.begin(), sInputFileName.end());
hr = cpInputStream->BindToFile(wInputFileName.c_str(), SPFM_OPEN_READONLY, &sInputFormat.FormatId(), sInputFormat.WaveFormatExPtr(), SPFEI_ALL_EVENTS);
hr = cpRecognizer->SetInput(cpInputStream, TRUE);
hr = cpRecognizer->CreateRecoContext(&cpRecoContext);
hr = cpRecoContext->CreateGrammar(NULL, &cpRecoGrammar);
hr = cpRecoGrammar->LoadDictation(NULL,SPLO_STATIC);
hr = cpRecoContext->SetNotifyWin32Event();
auto hEvent = cpRecoContext->GetNotifyEventHandle();
hr = cpRecoContext->SetInterest(SPFEI(SPEI_RECOGNITION) | SPFEI(SPEI_END_SR_STREAM), SPFEI(SPEI_RECOGNITION) | SPFEI(SPEI_END_SR_STREAM));
hr = cpRecoGrammar->SetDictationState(SPRS_ACTIVE);
BOOL fEndStreamReached = FALSE;
unsigned int timeOut = 0;
//WaitForSingleObject(hEvent, INFINITE);
while (!fEndStreamReached && S_OK == cpRecoContext->WaitForNotifyEvent(INFINITE)){
CSpEvent spEvent;
while (!fEndStreamReached && S_OK == spEvent.GetFrom(cpRecoContext)){
switch (spEvent.eEventId){
case SPEI_RECOGNITION:
{
auto pPhrase = spEvent.RecoResult();
SPPHRASE *phrase = nullptr;// new SPPHRASE();
LPWSTR* text = new LPWSTR(L"");
pPhrase->GetText(SP_GETWHOLEPHRASE, SP_GETWHOLEPHRASE, TRUE, text, NULL);
pPhrase->GetPhrase(&phrase);
if(phrase != NULL && phrase->pElements != NULL) {
std::wstring wRuleName = L"";
if(nullptr != phrase && phrase->Rule.pszName != NULL) {
wRuleName = phrase->Rule.pszName;
}
std::wstring recognizedText = L"";
bool firstWord = true;
for(ULONG i = 0; i < (ULONG)phrase->Rule.ulCountOfElements; ++i) {
if(phrase->pElements[i].pszDisplayText != NULL) {
std::wstring outString = phrase->pElements[i].pszDisplayText;
std::string soutString = std::string(outString.begin(), outString.end());
if(!firstWord){
soutString = " " + soutString;
firstWord = false;
}
soutString = soutString + " ";
fputs(soutString.c_str(),fp);
/*if(recognizedText != L"") {
recognizedText += L" " + outString;
} else {
recognizedText += outString;
}*/
}
}
}
delete[] text;
break;
}
case SPEI_END_SR_STREAM:
{
fEndStreamReached = TRUE;
break;
}
}
// clear any event data/object references
spEvent.Clear();
}
}
hr = cpRecoGrammar->SetDictationState(SPRS_INACTIVE);
hr = cpRecoGrammar->UnloadDictation();
hr = cpInputStream->Close();
fclose(fp);
}
}
closedir(dir);
} else {
perror("Error opening directory");
}
::CoUninitialize();
std::printf("Press any key to continue...");
std::getchar();
return 0;
}
我已经很久没有运行它了，但是你必须得到 dirent.h 才能让它工作。我在玩那个图书馆只是为了尝试一下。
使用提供的代码，您可能会开始查看在识别步骤中生成了哪些置信度值。如果您愿意，您还可以调整它以从批处理文件运行。
我遇到的问题如下：
- 准确性是个问题，为了改进它，我必须训练识别器，这将需要比我更多的时间。
- 我发现直接翻译成文本并不是我真正想要的。事实证明，音素数据更为重要。这样您就可以形成自己的置信度方案，并针对您的应用开发自己的替代方案。
- Window 的识别器虽然不错，但不会识别它不知道的单词。您必须弄清楚如何将您的词汇添加到 Windows 的语音识别器词典中。
话虽如此，使用现有的 Windows 桌面语音识别器并非易事。我会看看一些现有的 API。如果您不仅限于客户端应用程序，那么您最好研究一下其他 API。