음성 스팩트로그램 수정내용,

[Kownby]

• wav용 파일로 작성된 부분을 사용.

• amplitude 가 sample 값 이란 부분을 db로 변경

• 크기를 비율적으로 조절해서 사용하고 수치를 알수 있게 사용

• 코드 내용과 내용수정으로 볼수 있도록 사용

• 코드를 완전 바꾼거고 stackoverflow 에 있던 코드 사용 및 분석
  결과 사진.

• 배고픔3
  

• 배고픔3 200 db 이상.
  

• 아픔 3
  

• 아픔3 200 db 이상
  

• 잠 1
  

• 잠 1 db 200 이상.
  

코드 부분

`

import numpy as np
from matplotlib import pyplot as plt
import scipy.io.wavfile as wav
from numpy.lib import stride_tricks
filepath = 's1' + '.wav'

short time fourier transform of audio signal

def stft(sig, frameSize, overlapFac=0.5, window=np.hanning):
#sig = signal frameSize = 2 ** 10

win = window(frameSize)
hopSize = int(frameSize - np.floor(overlapFac * frameSize))

# zeros at beginning (thus center of 1st window should be for sample nr. 0)
samples = np.append(np.zeros(int(np.floor(frameSize/2.0))), sig)
print(samples)
# cols for windowing
cols = np.ceil( (len(samples) - frameSize) / float(hopSize)) + 1
# zeros at end (thus samples can be fully covered by frames)
samples = np.append(samples, np.zeros(frameSize))

frames = stride_tricks.as_strided(samples, shape=(int(cols), frameSize), strides=(samples.strides[0]*hopSize, samples.strides[0])).copy()
frames *= win

return np.fft.rfft(frames)

scale frequency axis logarithmically

def logscale_spec(spec, sr=44100, factor=20.):
timebins, freqbins = np.shape(spec)

scale = np.linspace(0, 1, freqbins) ** factor
scale *= (freqbins-1)/max(scale)
scale = np.unique(np.round(scale))

# create spectrogram with new freq bins
newspec = np.complex128(np.zeros([timebins, len(scale)]))
for i in range(0, len(scale)):
    if i == len(scale)-1:
        newspec[:,i] = np.sum(spec[:,int(scale[i]):], axis=1)
    else:
        newspec[:,i] = np.sum(spec[:,int(scale[i]):int(scale[i+1])], axis=1)

# list center freq of bins
allfreqs = np.abs(np.fft.fftfreq(freqbins*2, 1./sr)[:freqbins+1])
freqs = []
for i in range(0, len(scale)):
    if i == len(scale)-1:
        freqs += [np.mean(allfreqs[int(scale[i]):])]
    else:
        freqs += [np.mean(allfreqs[int(scale[i]):int(scale[i+1])])]

return newspec, freqs

plot spectrogram

def plotstft(audiopath, binsize=2**10, plotpath=None, colormap="jet"):
#sr , sample
samplerate, samples = wav.read(audiopath)

# s = stft
s = stft(samples, binsize)

print("lens",len(s[0]))


sshow, freq = logscale_spec(s, sr=samplerate, factor=1.0)

ims = 20.*np.log10(np.abs(sshow)/10e-6) # amplitude to decibel
timebins, freqbins = np.shape(ims)
print( ((len(samples) / timebins) + (0.5 * binsize)) / samplerate )


print("timebins: {0} freqbins: {1}\n".format(timebins,freqbins))
#print(ims)
x = ((len(samples)/timebins)+(0.5*binsize))/samplerate
print (x * timebins)
plt.figure(figsize=(15, 7.5))
plt.imshow(np.transpose(ims), origin="lower", aspect="auto", cmap=colormap, interpolation="none")
plt.colorbar()

plt.xlabel("time (s)")
plt.ylabel("frequency (hz)")
plt.xlim([0, timebins-1])
plt.ylim([0, freqbins])

xlocs = np.float32(np.linspace(0, timebins-1, 5))
print(xlocs)
plt.xticks(xlocs, ["%.02f" % l for l in ((xlocs*len(samples)/timebins)+(0.5*binsize))/samplerate])
ylocs = np.int16(np.round(np.linspace(0, freqbins-1, 10)))
plt.yticks(ylocs, ["%.02f" % freq[i] for i in ylocs])
print(ylocs)

if plotpath:
    plt.savefig(plotpath, bbox_inches="tight")
else:
    plt.savefig("spectrogram of %r.png" % audiopath)
    plt.show()

plt.clf()

return ims

ims = plotstft(filepath)
`