如何使用espeak_EVENT_TYPE；

Question

我正在寻找一种方法来知道espeak什么时候结束它的演讲。有人告诉我使用espeakEVENT_MSG_TERMINATED。但是，当我试图将这个部分放到我的代码中时，它会给出以下错误：

#include <espeak/speak_lib.h>

espeak_EVENT_TYPE;

    if( espeak_EVENT_TYPE == espeakEVENT_MSG_TERMINATED)
    {
    do something;
    }

application.cpp:31:1: error:声明不声明任何-fpermissive espeak_EVENT_TYPE；^ application.cpp:在函数‘void(char*)’：application.cpp:116:27: application.cpp:116:27：==令牌if之前的预期主表达式( espeak_EVENT_TYPE == espeakEVENT_MSG_TERMINATED)

编辑:我使用这个简单的代码来使用espeak

#include <string.h>
#include <malloc.h>
#include <espeak/speak_lib.h>


espeak_POSITION_TYPE position_type;
espeak_AUDIO_OUTPUT output;
char *path=NULL;
int Buflength = 1000, Options=0;
void* user_data;
t_espeak_callback *SynthCallback;
espeak_PARAMETER Parm;



char Voice[] = {"English"};


char text[30] = {"this is an english text"};
unsigned int Size,position=0, end_position=0, flags=espeakCHARS_AUTO, *unique_identifier;




int main(int argc, char* argv[] ) 
{
    output = AUDIO_OUTPUT_PLAYBACK;
    espeak_Initialize(output, Buflength, path, AUDIO_OUTPUT_SYNCHRONOUS ); //Options ); 
    espeak_SetVoiceByName(Voice);
    const char *langNativeString = "en";
    espeak_VOICE voice = {0};
  //  memset(&voice, 0, sizeof(espeak_VOICE));
        voice.languages = langNativeString;
        voice.name = "US";
        voice.variant = 2;
        voice.gender = 1;
        espeak_SetVoiceByProperties(&voice);
    Size = strlen(text)+1;    

    espeak_Synth( text, Size, position, position_type, end_position, flags,unique_identifier, user_data );
    espeak_Synchronize( );

    return 0;
}

Edit2：

#include <stdio.h>
#include <string.h>
#include <assert.h>

#include <sphinxbase/err.h>
#include <sphinxbase/ad.h>

#include <espeak/speak_lib.h>
#include <string>
#include <iostream>
using namespace std;

#include "pocketsphinx.h"
static ps_decoder_t *ps;
static cmd_ln_t *config;
static FILE *rawfd;

ad_rec_t *ad;

espeak_POSITION_TYPE position_type;
espeak_AUDIO_OUTPUT output;
char *path=NULL;
int Buflength = 1000, Options=0;
void* user_data;
char Voice[] = {"English"};
unsigned int Size,position=0, end_position=0, flags=espeakCHARS_AUTO, *unique_identifier;
t_espeak_callback *SynthCallback;
espeak_PARAMETER Parm;

static void initFuncs()
{

    output = AUDIO_OUTPUT_PLAYBACK;
    espeak_Initialize(output, Buflength, path, AUDIO_OUTPUT_SYNCHRONOUS ); 
    espeak_SetVoiceByName(Voice);
    const char *langNativeString = "en";
    espeak_VOICE voice;
    memset(&voice, 0, sizeof(espeak_VOICE));
        voice.languages = langNativeString;
        voice.name = "US";
        voice.variant = 2;
        voice.gender = 1;
        espeak_SetVoiceByProperties(&voice);

}

int receive_espeak_events(short *wav, int numsamples, espeak_EVENT *event)
{
    while (event->type != espeakEVENT_LIST_TERMINATED) {
        if (event->type == espeakEVENT_MSG_TERMINATED) {
            /* do something */
            ad_start_rec(ad);
        }
        ++event; // Examine the next event.
    }
    return 0; // Continue speaking.
}

static void sleep_msec(int32 ms)
{
    struct timeval tmo;

    tmo.tv_sec = 0;
    tmo.tv_usec = ms * 1000;

    select(0, NULL, NULL, NULL, &tmo);

}

static void speech(char* hyp)
{      
    Size = strlen(hyp)+1;
    espeak_SetSynthCallback(receive_espeak_events);
    espeak_Synth( hyp, Size, position, position_type, end_position, flags,unique_identifier, user_data );
    espeak_Synchronize( );    
}


static void recognize_from_microphone()
{

    ad_rec_t *ad;
    int16 adbuf[2048];
    uint8 utt_started, in_speech;
    int32 k;
    char  *hyp=0;

    if ((ad = ad_open_dev(cmd_ln_str_r(config, "-adcdev"),(int) cmd_ln_float32_r(config,"-samprate"))) == NULL)
        E_FATAL("Failed to open audio device\n");
    if (ad_start_rec(ad) < 0)
        E_FATAL("Failed to start recording\n");

    if (ps_start_utt(ps) < 0)
        E_FATAL("Failed to start utterance\n");


    utt_started = FALSE;
    E_INFO("Ready....\n");

    for (;;) 
    {

        if ((k = ad_read(ad, adbuf, 2048)) < 0)
            E_FATAL("Failed to read audio\n");
        ps_process_raw(ps, adbuf, k, FALSE, FALSE);
        in_speech = ps_get_in_speech(ps);
        if (in_speech && !utt_started) 
        {
            utt_started = TRUE;
            E_INFO("Listening...\n");
        }
        if (!in_speech && utt_started) 
        {

            ps_end_utt(ps);
            hyp = (char*)ps_get_hyp(ps, NULL );
            if (hyp != NULL) 
            {
///////////////////I am passing hyp to espeak heere ////////////////////
             ad_stop_rec(ad);
             speech(hyp);

                printf("%s\n",hyp);
                fflush(stdout);
            //    sleep_msec(3000);

            }

            if (ps_start_utt(ps) < 0)
                E_FATAL("Failed to start utterance\n");
            utt_started = FALSE;
            E_INFO("Ready....\n");

        }
    }//for
    ad_close(ad);
}

int main(int argc, char *argv[])
{
    initFuncs();

                 config = cmd_ln_init(NULL, ps_args(), TRUE,
                 "-hmm", "/home/m/myrobot3/robot/model_parameters/robot.cd_cont_1000",
                     "-lm","/home/m/myrobot3/robot/etc/robot.lm.bin",
                     "-dict", "/home/m/myrobot3/robot/etc/robot.dic",
                     NULL);

    ps = ps_init(config);
    recognize_from_microphone();

    ps_free(ps);
    cmd_ln_free_r(config);

    return 0;
}

错误：

致命："application.cpp"，第163行:无法读取音频

Answer 1

espeak_EVENT_TYPE;

这一行对编译器来说是不明智的。espeak_EVENT_TYPE是一种数据类型。它不是一个可以与espeakEVENT_MSG_TERMINATED这样的值相比较的变量。为了声明一个变量，语法是：

espeak_EVENT_TYPE an_event_type {};
if (an_event_type == espeakEVENT_MSG_TERMINATED) {
/* ... */

但是，如果我们这样做，那么我们刚刚创建的变量an_event_type实际上将不会包含任何关于实际espeak事件的信息。当然，对于是否终止任何实际消息，它也不会透露任何信息。

从espeak接收真实事件信息

为了获取有关消息是否终止的信息，程序需要从espe库中获取一个类型为espeak_EVENT_TYPE的变量。

纵观此标头，espeak_EVENT_TYPE被用作espeak_EVENT结构的一部分。要接收espeak_EVENT通知，必须编写一个函数，该函数将由espeak库调用。(这称为“回调”函数)。然后通过调用espeak_SetSynthCallback将回调函数注册到库中。

在相同的标题中，回调函数的原型必须如下：

int SynthCallback(短*wav，int数字样本，espeak_EVENT *事件)； wav:是已经产生的语音数据。NULL表示合成已经完成。 数字示例:是wav中的条目数。这个数字可能会变化，可能小于> espeak_Initialize中给出的buflength参数所暗示的值，有时可能为零(这并不表示合成的结束)。 事件:表示单词和句子事件以及文本中发生的if和元素的espeak_EVENT项的数组。事件列表被类型>= 0的事件终止。 回调返回: 0=continue合成，1=abort合成。

综合起来，我们需要一个函数来循环events变量，就像它是一个数组一样，直到它遇到0类型的事件。然后，函数需要返回0才能继续语音活动。

int receive_espeak_events(short *wav, int numsamples, espeak_EVENT *event)
{
    while (event->type != espeakEVENT_LIST_TERMINATED) {
        if (event->type == espeakEVENT_MSG_TERMINATED) {
            /* do something */
        }
        ++event; // Examine the next event.
    }
    return 0; // Continue speaking.
}

要告诉espeak调用此函数，请在开始任何综合操作之前将该函数传递给espeak_SetSynthCallback。

espeak_SetSynthCallback(receive_espeak_events);