在 Windows 環境下使用 SAPI 開發語音程式（二）： 程式碼概觀

我個人在 coding 的時候有個癖好，就是喜歡極簡風。所以當我要寫
一個軟體模組，我都會盡量堅持一個 .cpp 和一個 .hpp 。

先把 code 秀出來好了。

// SpeechRecognizer.hpp
#ifndef _SPEECHRECOGNIZER_HPP
#define _SPEECHRECOGNIZER_HPP

#include < sphelper.h >
#include < windows.h >

class SpeechRecognizer
{
public:
	void activate();
	void deactivate();
	static void thrRun(void*);

	void initSAPI();
	void cleanupSAPI();
	void executeCommand(ISpPhrase *pPhrase);
	void exitError(LPTSTR lpszFunction);
//protected:
	// for running
	bool _active;

	// for SAPI
	CComPtr< ISpRecoContext > _cpRecoCtxt;
	CComPtr< ISpRecoGrammar > _cpGrammar;
	CComPtr< ISpRecognizer >	_cpEngine;
};
#endif

##CONTINUE##

// SpeechRecognizer.cpp

#include "SpeechRecognizer.hpp"
#include < process.h >
#include < iostream >

using namespace std;

void SpeechRecognizer::activate()
{
	initSAPI();
	_active = true;
	_beginthread(SpeechRecognizer::thrRun, 0, this);
}

void SpeechRecognizer::deactivate()
{
	_active = false;
	cleanupSAPI();
}

void SpeechRecognizer::thrRun(void* ptr)
{
	SpeechRecognizer* pSR = (SpeechRecognizer*)ptr;

	HRESULT hr;
	while(pSR->_active){
		hr = pSR->_cpRecoCtxt->WaitForNotifyEvent(100);
		if(hr == 0){
			CSpEvent event;
			event.GetFrom(pSR->_cpRecoCtxt);
			pSR->executeCommand(event.RecoResult());
		}
	}
	_endthread();
}

void SpeechRecognizer::initSAPI()
{
	if(FAILED(::CoInitialize(NULL))){ exitError(TEXT("init COM Failed!")); }
	
	HRESULT hr;
	
    // create a recognition engine
	hr = _cpEngine.CoCreateInstance(CLSID_SpSharedRecognizer);
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpEngine.CoCreateInstance")); }

	// create the command recognition context
	hr = _cpEngine->CreateRecoContext( &_cpRecoCtxt );
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpEngine->CreateRecoContext")); }

	// Let SR know that window we want it to send event information to, and using
	// what message
	hr = _cpRecoCtxt->SetNotifyWin32Event();
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpRecoCtxt->SetNotifyWin32Event")); }

	// Tell SR what types of events interest us.  Here we only care about command
	// recognition.
	hr = _cpRecoCtxt->SetInterest(SPFEI(SPEI_RECOGNITION), SPFEI(SPEI_RECOGNITION));
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpRecoCtxt->SetInterest")); }

	// Load our grammar, which is the compiled form of simple.xml bound into this executable as a
	hr = _cpRecoCtxt->CreateGrammar(0, &_cpGrammar);
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpRecoCtxt->CreateGrammar")); }

	hr = _cpGrammar->LoadCmdFromFile(L"test.xml", SPLO_DYNAMIC);
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpCmdGrammar->LoadCmdFromFile")); }

	// Set rules to active, we are now listening for commands
	hr = _cpGrammar->SetRuleState(NULL, NULL, SPRS_ACTIVE);
	if(FAILED(hr)){ cleanupSAPI(); exitError(TEXT("_cpGrammar->SetRuleState")); }
}

void SpeechRecognizer::cleanupSAPI()
{
	// Release grammar, if loaded
    if (_cpGrammar){
		_cpGrammar.Release();
    }
    // Release recognition context, if created
    if (_cpRecoCtxt){
        _cpRecoCtxt->SetNotifySink(NULL);
        _cpRecoCtxt.Release();
    }
    // Release recognition engine instance, if created
	if (_cpEngine){
		_cpEngine.Release();
	}
	CoUninitialize();
}

void SpeechRecognizer::executeCommand(ISpPhrase *pPhrase)
{
	SPPHRASE* pElements;
	if(SUCCEEDED(pPhrase->GetPhrase(&pElements))){
		switch(pElements->Rule.ulId){
			case 1:
				cout << "robot" << endl;
				break;
			case 2:
				cout << "hello" << endl;
				break;
			default:
				;
		}
	}
}
void SpeechRecognizer::exitError(LPTSTR lpszFunction)
{
    // Retrieve the system error message for the last-error code
    LPVOID lpMsgBuf;
    LPVOID lpDisplayBuf;
    DWORD dw = GetLastError(); 
    FormatMessage(
        FORMAT_MESSAGE_ALLOCATE_BUFFER | 
        FORMAT_MESSAGE_FROM_SYSTEM |
        FORMAT_MESSAGE_IGNORE_INSERTS,
        NULL,
        dw,
        MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
        (LPTSTR) &lpMsgBuf,
        0, NULL );
    // Display the error message and exit the process
    lpDisplayBuf = (LPVOID)LocalAlloc(LMEM_ZEROINIT, 
        (lstrlen((LPCTSTR)lpMsgBuf) + lstrlen((LPCTSTR)lpszFunction) + 40) * sizeof(TCHAR)); 
    StringCchPrintf((LPTSTR)lpDisplayBuf, 
        LocalSize(lpDisplayBuf) / sizeof(TCHAR),
        TEXT("%s failed with error %d: %s"), 
        lpszFunction, dw, lpMsgBuf); 
    MessageBox(NULL, (LPCTSTR)lpDisplayBuf, TEXT("Error"), MB_OK); 

    LocalFree(lpMsgBuf);
    LocalFree(lpDisplayBuf);
    ExitProcess(dw); 
}

跟一般程式不同的地方在於， SAPI 需要「文法」，才能真正擁有語音辨識的能力。

通常關於文法需要由另一個 .xml 檔案提供。

	robot
	hello