Thursday, January 27, 2022

Ekstraksi Fitur Akustik dengan Torchaudio

Kode di bawah ini mengekstrak tiga fitur akustik -- spectrogram, melspectrogram, dan mfcc -- dari sebuah file audio "filename" (wav, mp3, ogg, flacc, dll). Ketiga fitur akustik tersebut merupakan fitur-fitur akustik terpenting dalam pemrosesan sinyal wicara. Keterangan singkat ada di dalam badan kode. Hasil plot ada di bawah kode.

###
#import torch
import torchaudio
from matplotlib import pyplot as plt
import librosa

# show torchaudio version
# torch.__version__
print(torchaudio.__version__)


def plot_spectrogram(spec, title=None, ylabel="freq_bin", aspect="auto",
                     xmax=None):
    fig, axs = plt.subplots(1, 1)
    axs.set_title(title or "Spectrogram (db)")
    axs.set_ylabel(ylabel)
    axs.set_xlabel("frame")
    im = axs.imshow(librosa.power_to_db(spec), origin="lower", aspect=aspect)
    if xmax:
        axs.set_xlim((0, xmax))
    fig.colorbar(im, ax=axs)
    plt.show(block=False)


filename = "/home/bagus/train_001.wav"  # change with your file
waveform, sample_rate = torchaudio.load(filename)

# Konfigurasi untuk spectrogam, melspectrogram, dan MFCC
n_fft = 1024
win_length = None  # jika None maka sama dengan n_fft
hop_length = 512   # y-axis in spec plot
n_mels = 64  # y-axis in melspec plot
fmin = 50
fmax = 8000
n_mfcc = 40  # must be smaller than n_mels, will be y-axis in plot

# definisi kelas untuk ekstraksi spektrogram
spectrogram = torchaudio.transforms.Spectrogram(
    n_fft=n_fft,
    win_length=win_length,
    hop_length=hop_length,
    center=True,
    pad_mode="reflect",
    power=2.0,
)

# Show plot of spectrogram
spec = spectrogram(waveform)
print(spec.shape)  # torch.Size([1, 513, 426])
plot_spectrogram(spec[0], title=f"Spectrogram - {str(filename)}")


## kelas untuk ekstraksi melspectrogram
melspectogtram = torchaudio.transforms.MelSpectrogram(
    sample_rate=sample_rate,
    n_fft=n_fft,
    win_length=win_length,
    hop_length=hop_length,
    n_mels=n_mels,
    f_min=fmin,
    f_max=fmax,
)

# Calculate melspec
melspec = melspectogtram(waveform)
melspec.shape # torch.Size([1, 513, 426])
plot_spectrogram(melspec[0], title=f"Melspectrogam - {str(filename)}")

## kelas untuk ekstraksi MFCC
mfcc_transform = torchaudio.transforms.MFCC(
    sample_rate=sample_rate,
    n_mfcc=n_mfcc,
    melkwargs={
      'n_fft': n_fft,
      'n_mels': n_mels,
      'hop_length': hop_length,
      'mel_scale': 'htk',
    }
)

# plot mfcc
mfcc = mfcc_transform(waveform)
print(mfcc.shape) # torch.Size([1, 40, 426])
plot_spectrogram(mfcc[0], title=f"MFCC - {str(filename)}")
###

Plot 


Related Posts Plugin for WordPress, Blogger...