W3 Trigger Word Detection

Course Q&A Deep Learning Specialization Sequence Models
1

Set the random seed

np.random.seed(18)
x, y = create_training_example(backgrounds[0], activates, negatives, Ty)

in the example, I could visualize the spectrogram in its corresponding labels. But how can I obtain the plot of the audio in the time domain, so I can see its specific patterns in the time domain before taking its STFT?

2

The reason spectrograms exist is because looking at the raw time-series data is typically not productive.