Question

您好，我一直在寻找在Linux（最好是Ubuntu）系统上播放和录制音频的方法。我目前正在开发一个voice recognition toolkit的前端，它会自动执行调整PocketSphinx和Julius语音模型所需的几个步骤。

有关音频输入/输出的替代方法的建议欢迎，以及对错误的修复。

以下是我目前用来播放.WAV文件的当前代码：

void Engine::sayText ( const string OutputText ) {
    string audioUri = "temp.wav";
    string requestUri = this->getRequestUri( OPENMARY_PROCESS , OutputText.c_str( ) );
    int error , audioStream;
    pa_simple *pulseConnection;
    pa_sample_spec simpleSpecs;
    simpleSpecs.format = PA_SAMPLE_S16LE;
    simpleSpecs.rate = 44100;
    simpleSpecs.channels = 2;

    eprintf( E_MESSAGE , "Generating audio for '%s' from '%s'..." , OutputText.c_str( ) , requestUri.c_str( ) );
    FILE* audio = this->getHttpFile( requestUri , audioUri );
    fclose(audio);
    eprintf( E_MESSAGE , "Generated audio.");

    if ( ( audioStream = open( audioUri.c_str( ) , O_RDONLY ) ) < 0 ) {
        fprintf( stderr , __FILE__": open() failed: %s\n" , strerror( errno ) );
        goto finish;
    }

    if ( dup2( audioStream , STDIN_FILENO ) < 0 ) {
        fprintf( stderr , __FILE__": dup2() failed: %s\n" , strerror( errno ) );
        goto finish;
    }

    close( audioStream );

    pulseConnection = pa_simple_new( NULL , "AudioPush" , PA_STREAM_PLAYBACK , NULL , "openMary C++" , &simpleSpecs , NULL , NULL , &error );

    for (int i = 0;;i++ ) {
        const int bufferSize = 1024;
        uint8_t audioBuffer[bufferSize];
        ssize_t r;
        eprintf( E_MESSAGE , "Buffering %d..",i);
        /* Read some data ... */
        if ( ( r = read( STDIN_FILENO , audioBuffer , sizeof (audioBuffer ) ) ) <= 0 ) {
            if ( r == 0 ) /* EOF */
                break;

            eprintf( E_ERROR , __FILE__": read() failed: %s\n" , strerror( errno ) );
    if ( pulseConnection )
        pa_simple_free( pulseConnection );

        }

        /* ... and play it */
        if ( pa_simple_write( pulseConnection , audioBuffer , ( size_t ) r , &error ) < 0 ) {
            fprintf( stderr , __FILE__": pa_simple_write() failed: %s\n" , pa_strerror( error ) );
    if ( pulseConnection )
        pa_simple_free( pulseConnection );

        }

        usleep(2);

    }
    /* Make sure that every single sample was played */
    if ( pa_simple_drain( pulseConnection , &error ) < 0 ) {
        fprintf( stderr , __FILE__": pa_simple_drain() failed: %s\n" , pa_strerror( error ) );
    if ( pulseConnection )
        pa_simple_free( pulseConnection );
    }    
}

注意：如果您希望将其余代码添加到此文件中，可以直接从Launchpad下载here。

更新：我尝试使用GStreamermm，但这不起作用：

    Glib::RefPtr<Pipeline> pipeline;
    Glib::RefPtr<Element> sink, filter, source;
    Glib::RefPtr<Gio::File> audioSrc = Gio::File::create_for_path(uri);

    pipeline = Pipeline::create("audio-playback");
    source = ElementFactory::create_element("alsasrc","source");
    filter = ElementFactory::create_element("identity","filter");
    sink = ElementFactory::create_element("alsasink","sink");
    //sink->get_property("file",audioSrc);
    if (!source || !filter || !sink){
        showErrorDialog("Houston!","We got a problem.");
        return;
    }
    pipeline->add(source)->add(filter)->add(sink);
    source->link(sink);

    pipeline->set_state(Gst::STATE_PLAYING);
    showInformation("Close this to stop recording");
    pipeline->set_state(Gst::STATE_PAUSED);

Answer 1

The "Hello World" application in the GStreamer documentation显示了如何播放Ogg / Vorbis文件。要使用WAV文件，只需将“oggdemux”替换为“wavparse”，将“vorbisdec”替换为“identity”（身份插件不执行任何操作 - 它只是一个占位符）。

安装GStreamer的开发支持（在Ubuntu上）......

sudo apt-get install libgstreamer0.10-dev

您需要在gcc命令行上执行以下操作才能启用GStreamer库...

$(pkg-config --cflags --libs gstreamer-0.10)

顺便说一句，您可能会发现在编写代码之前使用“gst-launch”对GStreamer管道进行原型设计很有用。

## recording
gst-launch-0.10 autoaudiosrc ! wavenc ! filesink location=temp.wav

## playback
gst-launch-0.10 filesrc location=temp.wav ! wavparse ! autoaudiosink

可能对语音识别有用的GStreamer功能是可以轻松地将音频质量过滤器插入管道中 - 例如，您可以减少录音中可能存在的噪音。指向GStreamer“好”插件列表的指针是here。

同样有趣的是，“PocketSphinx”（似乎与您的项目有关）已经有了一些GStreamer集成。见Using PocketSphinx with GStreamer and Python

Answer 2

GStreamer / Pulse / JACK很棒。对于简单快速的事情，您可以使用SoX http://sox.sourceforge.net/

你如何在Linux上用C ++播放或录制音频（到.WAV）？

2 个答案: