import numpy as np
import numpy.random as random
from numpy.fft import fft
from scipy.io import wavfile
import matplotlib.pyplot as plt
import seaborn as sns
import os
%matplotlib inline
sns.set()
sns.set(font_scale=1.5)
data_dir = './recordings/'
# determine digits of interest (0 to 9)
digits = [1,2] # change here to load more digits
# dictionary that will store our values
signals = {d:[] for d in digits}
file_names = {d:[] for d in digits}
# import files
for filename in os.listdir(data_dir):
# iterate over digits
for d in digits:
if filename.startswith(str(d)+'_'):
wav = wavfile.read(data_dir+filename)[1]
if len(wav.shape)<2:
signals[d].append(wav)
file_names[d].append(filename)
# find maximum of vector length
N = max([len(v) for d in digits for v in signals[d]])
/shared-libs/python3.7/py-core/lib/python3.7/site-packages/ipykernel_launcher.py:15: WavFileWarning: Chunk (non-data) not understood, skipping it.
from ipykernel import kernelapp as app
# next we split our dataset in train and test
# we will use a 80/20 random split.
# create train/test split
ix = np.arange(100)
random.shuffle(ix)
# select train entries
ix_train = ix[:80]
#select test entries
ix_test = ix[80:]
# next we compute the average spectrum of each spoken digit in the training set.
# we will consider a window up to 1.5 KHz
# sampling rate is 8kHz
Ts = 1.0/8000
ix_cut = int(np.ceil(1500*Ts*N))
# initialize dictionary for storing transforms
transforms = {}
# initialize dictionary for storing mean transforms
mean_transforms = {}
# compute mean transform of each digit and in the training set.
# Make sure to only keep the spectrum up to 1.5kHz
# Code Solution to Q1 Here
# In this next part, plot the average spectral magnitude of each digit.
# Code Solution to Q2 here
# classifier function
# receives a vector, computes the product with average digits, and returns the max inner product
# Input: sample x (vector)
def mean_classifier(x):
SyntaxError: unexpected EOF while parsing (<ipython-input-8-809ee030bff3>, line 5)
# Code Q3a Here
# Write anser for Q3b here
# Code 3b Here
{1: 0.05, 2: 0.05}
# Write answer for Q4 here
# Code Q4 here
/shared-libs/python3.7/py-core/lib/python3.7/site-packages/ipykernel_launcher.py:16: WavFileWarning: Chunk (non-data) not understood, skipping it.
app.launch_new_instance()
Error rates:
{0: 0.55, 1: 0.75, 2: 0.15, 3: 0.9, 4: 0.6, 5: 1.0, 6: 1.0, 7: 1.0, 8: 0.75, 9: 0.75}
# Write your answer here
Error rates 1-NN:
{0: 0.35, 1: 0.35, 2: 0.35, 3: 0.5, 4: 0.35, 5: 0.3, 6: 0.1, 7: 0.35, 8: 0.4, 9: 0.2}
Not great, but better than before...