def AnalyzeAudio(filename, database, numSongs):
# Audio sample to be analyzed and identified
# print('Please enter an audio sample file to identify: ')
userinput = filename
sample = read(userinput)
userinput = userinput.split(separator, 1)[0]
print('Analyzing the audio sample: ' + str(userinput))
srate = sample[0] # sample rate in samples/second
audio = sample[1] # audio data
spectrogram = tdft.tdft(audio, srate, windowsize, windowshift, fftsize)
time = spectrogram.shape[0]
freq = spectrogram.shape[1]
# print('The size of the spectrogram is time: ' + str(time) + ' and freq: ' + str(freq))
threshold = pp.find_thres(spectrogram, percentile, base)
peaks = pp.peak_pick(spectrogram, f_dim1, t_dim1, f_dim2, t_dim2,
threshold, base)
# print('The initial number of peaks is:' + str(len(peaks)))
peaks = pp.reduce_peaks(peaks, fftsize, high_peak_threshold,
low_peak_threshold)
# print('The reduced number of peaks is:' + str(len(peaks)))
# Store information for the spectrogram graph
samplePeaks = peaks
sampleSpectro = spectrogram
hashSample = fhash.hashSamplePeaks(peaks, delay_time, delta_time,
delta_freq)
# print('The dimensions of the hash matrix of the sample: ' + str(hashSample.shape))
# print('Attempting to identify the sample audio clip.')
timepairs = fhash.findTimePairs(database, hashSample, TPdelta_freq,
TPdelta_time)
# print(timepairs)
# Compute number of matches by song id to determine a match
songbins = np.zeros(numSongs)
numOffsets = len(timepairs)
offsets = np.zeros(numOffsets)
index = 0
for i in timepairs:
offsets[index] = i[0] - i[1]
index = index + 1
songbins[int(i[2])] += 1
# Identify the song
print('The sample song is: ' + str(songnames[np.argmax(songbins)]))
targetTracksId = songnames[np.argmax(songbins)][:-4]
targetTracksId = str(int(targetTracksId))
print('The sample song-genre is: ' + dict[targetTracksId])
return dict[targetTracksId] #str
for i in range(0, len(songs)):
print('Analyzing id=' + str(i) + ': ' + str(songnames[i]))
srate = songs[i][0] #sample rate in samples/second
audio = songs[i][1] #audio data
print('The srate of the audio is: ' + str(srate))
spectrogram = tdft.tdft(audio, srate, windowsize, windowshift, fftsize)
time = spectrogram.shape[0]
freq = spectrogram.shape[1]
print('The size of the spectrogram is time: ' + str(time) +
' and freq: ' + str(freq))
duration = time * windowshift
print('The duration of the song is: %.2f' % duration)
durations.append(duration)
threshold = pp.find_thres(spectrogram, percentile, base, top)
peaks = pp.peak_pick(spectrogram, f_dim1, t_dim1, f_dim2, t_dim2,
threshold, base, top)
print('The initial number of peaks is:' + str(len(peaks)))
peaks = pp.reduce_peaks(peaks, fftsize, high_peak_threshold,
low_peak_threshold)
print('The reduced number of peaks is:' + str(len(peaks)))
print('The 3 front element of reduced peaks:' + str(peaks[:3]))
#Calculate the hashMatrix for the database song file
songid = i
hashMatrix = fhash.hashPeaks(peaks, songid, delay_time, delta_time,
delta_freq)
print('hashMatrix of shape:' + str(hashMatrix.shape))
#Construct the audio database of hashes
database = np.zeros((1,5))
spectrodata = []
peaksdata = []
for i in range(0,len(songs)):
print('Analyzing '+str(songnames[i]))
srate = songs[i][0] #sample rate in samples/second
audio = songs[i][1] #audio data
spectrogram = tdft.tdft(audio, srate, windowsize, windowshift, fftsize)
time = spectrogram.shape[0]
freq = spectrogram.shape[1]
threshold = pp.find_thres(spectrogram, percentile, base)
print('The size of the spectrogram is time: '+str(time)+' and freq: '+str(freq))
spectrodata.append(spectrogram)
peaks = pp.peak_pick(spectrogram,f_dim1,t_dim1,f_dim2,t_dim2,threshold,base)
print('The initial number of peaks is:'+str(len(peaks)))
peaks = pp.reduce_peaks(peaks, fftsize, high_peak_threshold, low_peak_threshold)
print('The reduced number of peaks is:'+str(len(peaks)))
peaksdata.append(peaks)
#Calculate the hashMatrix for the database song file
songid = i
hashMatrix = fhash.hashPeaks(peaks,songid,delay_time,delta_time,delta_freq)