void setup() {
    stream.setLabelsForAllDimensions({"x", "y", "z"});
    useInputStream(stream);

    DTW dtw(false, true, null_rej);
    dtw.enableTrimTrainingData(true, 0.1, 75);

    pipeline.setClassifier(dtw);
    pipeline.addPostProcessingModule(ClassLabelTimeoutFilter(timeout));
    usePipeline(pipeline);

    registerTuneable(
        null_rej, 0.1, 5.0, "Variability",
        "How different from the training data a new gesture can be and "
        "still be considered the same gesture. The higher the number, the "
        "more different it can be.",
        [](double new_null_rej) {
            pipeline.getClassifier()->setNullRejectionCoeff(new_null_rej);
            pipeline.getClassifier()->recomputeNullRejectionThresholds();
        });

    registerTuneable(
        timeout, 1, 3000, "Timeout",
        "How long (in milliseconds) to wait after recognizing a "
        "gesture before recognizing another one.",
        [](double new_timeout) {
            ClassLabelTimeoutFilter* filter =
                dynamic_cast<ClassLabelTimeoutFilter*>(
                    pipeline.getPostProcessingModule(0));
            assert(filter != nullptr);
            filter->setTimeoutDuration(new_timeout);
        });
}
Beispiel #2
0
void setup() {
    stream.setLabelsForAllDimensions({"audio"});

    pipeline.addFeatureExtractionModule(
        FFT(kFftWindowSize, kFftHopSize,
            DIM, FFT::HAMMING_WINDOW, true, false));

    MFCC::Options options;
    options.sample_rate = kSampleRate;
    options.fft_size = kFftWindowSize / 2;
    options.start_freq = 300;
    options.end_freq = 3700;
    options.num_tri_filter = 26;
    options.num_cepstral_coeff = 12;
    options.lifter_param = 22;
    options.use_vad = true;
    options.noise_level = noise_level;

    pipeline.addFeatureExtractionModule(MFCC(options));

    pipeline.setClassifier(SVM());
    // GMM(16, true, false, 1, 100, 0.001));

    // In post processing, we wait #n predicitons. If m out of n predictions are
    // from the same class, we declare the class as the right one.
    //
    // n = (duration * sample_rate) / frame_size
    //   where duration    = post_duration
    //         sample_rate = kSampleRate
    //         frame_size  = kFftHopSize
    // m = n * post_ratio
    int num_predictions = post_duration / 1000 * kSampleRate / kFftHopSize;
    pipeline.addPostProcessingModule(
            ClassLabelFilter(num_predictions * post_ratio, num_predictions));

    auto ratio_updater = [](double new_ratio) {
        ClassLabelFilter* filter =
            dynamic_cast<ClassLabelFilter*>(pipeline.getPostProcessingModule(0));
        // Recalculate num_predictions as post_duration might have been changed
        int num_predictions = post_duration / 1000 * kSampleRate / kFftHopSize;
        filter->setMinimumCount(new_ratio * num_predictions);
    };

    auto duration_updater = [](int new_duration) {
        ClassLabelFilter* filter =
            dynamic_cast<ClassLabelFilter*>(pipeline.getPostProcessingModule(0));
        // Recalculate num_predictions as post_duration might have been changed
        int num_predictions = post_duration / 1000 * kSampleRate / kFftHopSize;
        filter->setBufferSize(num_predictions);
    };

    auto noise_updater = [](int new_noise_level) {
        MFCC *mfcc = dynamic_cast<MFCC*>(pipeline.getFeatureExtractionModule(1));
        mfcc->setNoiseLevel(new_noise_level);
    };

    registerTuneable(noise_level, 0, 20,
                     "Noise Level",
                     "The threshold for the system to distinguish between "
                     "ambient noise and speech/sound",
                     noise_updater);

    registerTuneable(post_duration, 0, 2000,
                     "Duration",
                     "Time (in ms) that is considered as a whole "
                     "for smoothing the prediction",
                     duration_updater);

    registerTuneable(post_ratio, 0.0f, 1.0f,
                     "Ratio",
                     "The portion of time in duration that "
                     "should be from the same class",
                     ratio_updater);

    useInputStream(stream);
    useOutputStream(oStream);
    usePipeline(pipeline);
    useLeaveOneOutScoring(false);
    setGUIBufferSize(kSampleRate);
}