windows - SAPI:语音转文本示例

Question

我是 SAPI 的新手，如果你们中的任何人能给我一个演讲来用 SAPI 文本 Hello World 示例，我将不胜感激。我知道 MS 有一些例子，如“听写”等，但我想从一个非常小的例子开始。很高兴能为您提供帮助。

Answer 1

我使用 SAPI 玩了一下 Windows 语音识别，它确实不是用户友好的。这是我编写的代码示例(用 C++):

#include <sphelper.h>
#include <sapi.h>
#include <iostream>
#include <string>

const ULONGLONG grammarId = 0;
const wchar_t* ruleName1 = L"ruleName1";

int start_listening(const std::string& word);
ISpRecoGrammar* init_grammar(ISpRecoContext* recoContext, const std::string& command);
void get_text(ISpRecoContext* reco_context);
void check_result(const HRESULT& result);

int main(int argc, char** argv)
{
    start_listening("Hello");
    return EXIT_SUCCESS;
}

// This function exits when the word passed as parameter is said by the user
int start_listening(const std::string& word)
{
    // Initialize COM library
    if (FAILED(::CoInitialize(nullptr))) {
        return EXIT_FAILURE;
    }

    std::cout << "You should start Windows Recognition" << std::endl;
    std::cout << "Just say \""<< word << "\"" << std::endl;

    HRESULT hr;

    ISpRecognizer* recognizer;
    hr = CoCreateInstance(CLSID_SpSharedRecognizer,
        nullptr, CLSCTX_ALL, IID_ISpRecognizer,
        reinterpret_cast<void**>(&recognizer));
    check_result(hr);

    ISpRecoContext* recoContext;
    hr = recognizer->CreateRecoContext(&recoContext);
    check_result(hr);

    // Disable context
    hr = recoContext->Pause(0);
    check_result(hr);

    ISpRecoGrammar* recoGrammar = init_grammar(recoContext, word);

    hr = recoContext->SetNotifyWin32Event();
    check_result(hr);

    HANDLE handleEvent;
    handleEvent = recoContext->GetNotifyEventHandle();
    if(handleEvent == INVALID_HANDLE_VALUE) {
        check_result(E_FAIL);
    }

    ULONGLONG interest;
    interest = SPFEI(SPEI_RECOGNITION);
    hr = recoContext->SetInterest(interest, interest);
    check_result(hr);

    // Activate Grammar
    hr = recoGrammar->SetRuleState(ruleName1, 0, SPRS_ACTIVE);
    check_result(hr);

    // Enable context
    hr = recoContext->Resume(0);
    check_result(hr);

    // Wait for reco
    HANDLE handles[1];
    handles[0] = handleEvent;
    WaitForMultipleObjects(1, handles, FALSE, INFINITE);
    get_text(recoContext);

    std::cout << "Hello user" << std::endl;

    recoGrammar->Release();
    ::CoUninitialize();

    system("PAUSE");
    return EXIT_SUCCESS;
}

/**
* Create and initialize the Grammar.
* Create a rule for the grammar.
* Add word to the grammar.
*/
ISpRecoGrammar* init_grammar(ISpRecoContext* recoContext, const std::string& command)
{
    HRESULT hr;
    SPSTATEHANDLE sate;

    ISpRecoGrammar* recoGrammar;
    hr = recoContext->CreateGrammar(grammarId, &recoGrammar);
    check_result(hr);

    WORD langId = MAKELANGID(LANG_FRENCH, SUBLANG_FRENCH);
    hr = recoGrammar->ResetGrammar(langId);
    check_result(hr);
    // TODO: Catch error and use default langId => GetUserDefaultUILanguage()

    // Create rules
    hr = recoGrammar->GetRule(ruleName1, 0, SPRAF_TopLevel | SPRAF_Active, true, &sate);
    check_result(hr);

    // Add a word
    const std::wstring commandWstr = std::wstring(command.begin(), command.end());
    hr = recoGrammar->AddWordTransition(sate, NULL, commandWstr.c_str(), L" ", SPWT_LEXICAL, 1, nullptr);
    check_result(hr);

    // Commit changes
    hr = recoGrammar->Commit(0);
    check_result(hr);

    return recoGrammar;
}

void get_text(ISpRecoContext* reco_context)
{
    const ULONG maxEvents = 10;
    SPEVENT events[maxEvents];

    ULONG eventCount;
    HRESULT hr;
    hr = reco_context->GetEvents(maxEvents, events, &eventCount);

    // Warning hr equal S_FALSE if everything is OK 
    // but eventCount < requestedEventCount
    if(!(hr == S_OK || hr == S_FALSE)) {
        check_result(hr);
    }

    ISpRecoResult* recoResult;
    recoResult = reinterpret_cast<ISpRecoResult*>(events[0].lParam);

    wchar_t* text;
    hr = recoResult->GetText(SP_GETWHOLEPHRASE, SP_GETWHOLEPHRASE, FALSE, &text, NULL);
    check_result(hr);

    CoTaskMemFree(text);
}

void check_result(const HRESULT& result)
{
    if (result == S_OK) {
        return;
    }

    std::string message;

    switch(result) {

    case E_INVALIDARG:
        message = "One or more arguments are invalids.";

    case E_ACCESSDENIED:
        message = "Acces Denied.";

    case E_NOINTERFACE:
        message = "Interface does not exist.";

    case E_NOTIMPL:
        message = "Not implemented method.";

    case E_OUTOFMEMORY:
        message = "Out of memory.";

    case E_POINTER:
        message = "Invalid pointer.";

    case E_UNEXPECTED:
        message = "Unexpecter error.";

    case E_FAIL:
        message = "Failure";

    default:
        message = "Unknown : " + std::to_string(result);
    }

    throw std::exception(message.c_str());
}

正如我所说，这有点复杂。我认为您应该将所有这些代码打包到一个库中，以使其更易于使用。