Notebook

• Visualization of the recordings - input features
  • 1.1. Wave and spectrogram
  • 1.2. MFCC
  • 1.3. Sprectrogram in 3d
  • 1.4. Silence removal
  • 1.5. Resampling - dimensionality reductions
  • 1.6. Features extraction steps
• Dataset investigation
  • 2.1. Number of files
  • 2.2. Mean spectrograms and fft
  • 2.3. Deeper into recordings
  • 2.4. Length of recordings
  • 2.5. Note on Gaussian Mixtures modeling
  • 2.6. Frequency components across the words
  • 2.7. Anomaly detection
• 3.Where to look for the inspiration

The libraries requires are as follows

import os
from os.path import isdir, join
from pathlib import Path
import pandas as pd

# Math
import numpy as np
from scipy.fftpack import fft
from scipy import signal
from scipy.io import wavfile
import librosa

from sklearn.decomposition import PCA

# Visualization
import matplotlib.pyplot as plt
import seaborn as sns
import IPython.display as ipd
import librosa.display

import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls
import pandas as pd

%matplotlib inline

[0]

https://www.kaggle.com/davids1992/speech-representation-and-data-exploration