一个超简单的语音识别编程，听写程序

Posted 2022-08-28 尹成

CSpeechRecognition类封装了语音识别操作所需调用的几个接口，使用它进行语音识别编程很方便，也很简洁。

CSpeechRecognition类的定义如下：

///

// active speech engine

#include <atlbase.h>

extern CComModule _Module;

#include <atlcom.h>

#include <sapi.h>

#include <sphelper.h>

#include <spuihelp.h>

///

// speech message

#define WM_SREVENT   WM_USER+102

 

class CSpeechRecognition 

public:

   CSpeechRecognition();

   virtual ~CSpeechRecognition();

 

   // initialize

   BOOL Initialize(HWND hWnd = NULL, BOOL bIsShared = TRUE);

   void Destroy();

 

   // start and stop

   BOOL Start();

   BOOL Stop();

   BOOL IsDictationOn()

  

       return m_bOnDictation;

  

 

   // event handler

   void GetText(WCHAR **ppszCoMemText, ULONG ulStart = 0, ULONG nlCount = -1);

 

   // voice training

   HRESULT VoiceTraining(HWND hWndParent);

 

   // microphone setup

   HRESULT MicrophoneSetup(HWND hWndParent);

 

   // token list

   HRESULT InitTokenList(HWND hWnd, BOOL bIsComboBox = FALSE);

 

   // error string

   CString GetErrorString()

  

       return m_sError;

  

 

   // interface

     CComPtr<ISpRecognizer> m_cpRecoEngine;  // SR engine

       CComPtr<ISpRecoContext> m_cpRecoCtxt;   //Recognition contextfor dictation

     CComPtr<ISpRecoGrammar> m_cpDictationGrammar;  // Dictation grammar

 

private:

   CString m_sError;

    BOOL    m_bOnDictation;

;

其中定义的消息WM_SREVENT用于指示语音识别事件，该消息将通知到初始化函数指定的响应窗口。

类中定义了3个接口指针m_cpRecoEngine，m_cpRecoCtxt和m_cpDictationGrammar，分别用于引用语音识别引擎的3个重要接口IspRecognizer，ISpRecoContext和IspRecoGrammar。

初始化函数Initialize设定了语音识别引擎的基本工作环境，包括引擎、识别上下文、语法、音频和事件等的初始化：

BOOL CSpeechRecognition::Initialize(HWND hWnd, BOOL bIsShared)

   // com library

   if (FAILED(CoInitialize(NULL)))

  

       m_sError=_T("Error intialization COM");

       return FALSE;

  

 

   // SR engine

    HRESULT hr = S_OK;

    if (bIsShared)

   

        // Shared reco engine.

        // For a shared reco engine, the audio gets setup automatically

        hr = m_cpRecoEngine.CoCreateInstance( CLSID_SpSharedRecognizer );

   

   else

  

       hr = m_cpRecoEngine.CoCreateInstance(CLSID_SpInprocRecognizer);

 

  

 

   // RecoContext

    if( SUCCEEDED( hr ) )

   

        hr = m_cpRecoEngine->CreateRecoContext( &m_cpRecoCtxt );

   

 

    // Set recognition notification for dictation

    if (SUCCEEDED(hr))

   

  hr = m_cpRecoCtxt->SetNotifyWindowMessage( hWnd, WM_SREVENT, 0, 0 );

   

   

    if (SUCCEEDED(hr))

   

        // when the engine has recognized something

        const ULONGLONG ullInterest = SPFEI(SPEI_RECOGNITION);

        hr = m_cpRecoCtxt->SetInterest(ullInterest, ullInterest);

   

 

    // create default audio object

    CComPtr<ISpAudio> cpAudio;

    hr = SpCreateDefaultObjectFromCategoryId(SPCAT_AUDIOIN, &cpAudio);

 

    // set the input for the engine

    hr = m_cpRecoEngine->SetInput(cpAudio, TRUE);

    hr = m_cpRecoEngine->SetRecoState( SPRST_ACTIVE );

 

   // grammar

    if (SUCCEEDED(hr))

   

        // Specifies that the grammar we want is a dictation grammar.

        // Initializes the grammar (m_cpDictationGrammar)

        hr = m_cpRecoCtxt->CreateGrammar( 0, &m_cpDictationGrammar );

   

    if  (SUCCEEDED(hr))

    hr = m_cpDictationGrammar->LoadDictation(NULL, SPLO_STATIC);

   

    if (SUCCEEDED(hr))

   

        hr = m_cpDictationGrammar->SetDictationState( SPRS_ACTIVE );

   

    if (FAILED(hr))

   

        m_cpDictationGrammar.Release();

   

 

    return (hr == S_OK);

 

释放函数Destroy被类的析构函数调用，释放了类所引用的所有接口：

void CSpeechRecognition::Destroy()

   if (m_cpDictationGrammar)

       m_cpDictationGrammar.Release();

   if (m_cpRecoCtxt)

       m_cpRecoCtxt.Release();

   if (m_cpRecoEngine)

       m_cpRecoEngine.Release();

   CoUninitialize();

函数Start和Stop用来控制开始和停止接受及识别语音，它们通过调用引擎接口的SetRecoState方法来实现：

BOOL CSpeechRecognition::Start()

   if (m_bOnDictation)

       return TRUE;

 

         HRESULT hr = m_cpRecoEngine->SetRecoState( SPRST_ACTIVE );

   if (FAILED(hr))

         return FALSE;

 

   m_bOnDictation = TRUE;

   return TRUE;

 

BOOL CSpeechRecognition::Stop()

   if (! m_bOnDictation)

       return TRUE;

 

       HRESULT hr = m_cpRecoEngine->SetRecoState( SPRST_INACTIVE );

   if (FAILED(hr))

return FALSE;

 

   m_bOnDictation = FALSE;

   return TRUE;

函数GetText是获取从语音中已识别出的文字的关键