PSet7-Shazam - Duplicate

from pydub import AudioSegment from scipy import signal from operator import itemgetter import pyaudio import numpy as np import utils import os import sys import warnings import operator import matplotlib.mlab as mlab import matplotlib.pyplot as plt import math from itertools import islice

FORMAT = pyaudio.paInt16 ''' Number of audio channels in the recording ''' CHANNELS = 2 ''' Original sample rate of the recordings ''' SAMPLE_RATE = 44100 ''' Sampling rate (after downsampling) ''' FS = 8000 ''' Factor by which the original signal will be downsampled ''' DECIMATION_FACTOR = SAMPLE_RATE/FS ''' Size of the FFT window, affects frequency granularity (we saw this in class!) ''' WINDOW_SIZE = 1024 ''' Degree to which a fingerprint can be paired with its neighbors -- higher will cause more fingerprints, but potentially better accuracy. ''' FAN_VALUE = 15 ''' Ratio by which each window overlaps the previous and next window -- higher will cause more fingerprints, but higher granularity of offset matching ''' OVERLAP_RATIO = 0.5 path = os.getcwd() warnings.filterwarnings("ignore", message="divide by zero encountered in log10") warnings.filterwarnings("ignore", category=DeprecationWarning)

# Database with key=songname, value=[channel1, channel2] SongDb = {} #Goes through mp3s folder and adds each song to database for filename in os.listdir(path + "/mp3s/"): audiofile = AudioSegment.from_file(path + "/mp3s/" + filename) data = np.fromstring(audiofile._data, np.int16) channels = [] for chn in range(audiofile.channels): channels.append(data[chn::audiofile.channels]) SongDb[filename[:-3]] = channels print("Added to song database: " + str(filename[:-4]))

def Preprocess(channels): channel1 = channels[0] channel2 = channels[1] channelmean = ((channel1 + channel2)/2 - np.mean(channel1 + channel2)) resampled = signal.decimate(channelmean, int(DECIMATION_FACTOR)) return resampled

# Database with key=songname, value=processed signal ProcessedDb = {} #Processes each song and adds it to ProcessedDb #Prints table of number of samples in for each song print('{0:65}{1:22}{2:20}\n'.format('Song Name', 'Original #Samples', 'Processed #Samples')) for song, sig in SongDb.items(): processed = Preprocess(sig) ProcessedDb[song] = processed original_duration = len(sig[0]) processed_duration = len(processed) print('{0:50}{1:32d}{2:20d}'.format(song, original_duration, processed_duration))

def getSpectrogram(signal): spec_H1, freqs, t = mlab.specgram(signal, NFFT = WINDOW_SIZE, Fs = FS, noverlap = WINDOW_SIZE*OVERLAP_RATIO) spec_H1[np.nonzero((spec_H1 == np.inf) | (spec_H1 == -np.inf))] = 0 spec_H1 = 10*np.log10(spec_H1) return spec_H1

''' TODO ''' # Database with key=songname, value=spectrogram Spectrograms = {} for i in ProcessedDb: spectogram = getSpectrogram(ProcessedDb[i]) Spectrograms[i] = spectogram plt.imshow(spectogram) plt.title(i) plt.show() # Gets the spectrogram for each song and adds it to the Spectrograms database # Plots each spectrogram

''' TODO ''' # Database with key=songname, value=array of local peaks Peaks = {} for i in Spectrograms: peaks_output = utils.get_2D_peaks(Spectrograms[i]) Peaks[i] = list(peaks_output[2]) plt.imshow(Spectrograms[i]) plt.plot(peaks_output[1], peaks_output[0], '*', markersize = '1') plt.title(i) plt.show() # Gets the local peaks for each song and adds it to the Peaks database # Plots the peaks over the original spectrogram

def getPairs(peaks): peaks = list(peaks) no_of_pairs = {} pairs = [] counter = 1 for j in range(len(peaks)): no_of_pairs[peaks[j]] = 0 for i in range(len(peaks)): current = peaks[i] for j in range(len(peaks)): pair = peaks[j] time_diff = pair[1] - current[1] if pair != current and abs(time_diff) <= 150 and no_of_pairs[current] < 15 and no_of_pairs[pair] < 15: pairs.append((current[0], pair[0], time_diff)) no_of_pairs[current] += 1 no_of_pairs[pair] += 1 return pairs

''' TODO ''' # Database with key=fingerprint (f1, f2, tdelta), value=songname # Get fingerprints for each song stores them in the LookUpTable database LookUpTable = {} for i in Peaks: pairs = getPairs(Peaks[i]) for j in range(len(pairs)): LookUpTable[pairs[j]] = i # Prints a sample of the LookUpTable entries dict(islice(LookUpTable.items(), 0, 250))

# Database with key=songname, value=[channel1, channel2] for a snippet of the song TestDb = {} # Goes through test_mp3s folder and adds a snippet of each song to database for filename in os.listdir("./test_mp3s/"): audiofile = AudioSegment.from_file("./test_mp3s/" + filename) data = np.fromstring(audiofile._data, np.int16)[SAMPLE_RATE*60:SAMPLE_RATE*75] channels = [] for chn in range(audiofile.channels): channels.append(data[chn::audiofile.channels]) TestDb[filename] = channels print("Added to test database. : " + str(filename))

# Goes through test snippets and runs same fingerprinting process # Prints out the number of matches for each song and confidence of prediction for test in TestDb.keys(): print('\033[1mTesting: ' + test + '\033[0m \n') Matches = {} for song in SongDb.keys(): Matches[song] = 0 channels = TestDb[test] preprocessed = Preprocess(channels) spectrogram = getSpectrogram(preprocessed) _, _, peaks = utils.get_2D_peaks(spectrogram) pairs = getPairs(peaks) for p in pairs: match = LookUpTable.get(p, None) if match: Matches[match] += 1 prediction, count = max(Matches.items(), key=itemgetter(1)) for k,v in Matches.items(): if k == prediction: print('\033[1m{0:50} ==> {1:10d} \033[0m'.format(k, v)) else: print('{0:50} ==> {1:10d}'.format(k, v)) confidence = str(float(count)/sum(Matches.values())*100)[:5] + "%" prediction = max(Matches.items(), key=itemgetter(1)) print(f'\nPrediction: {prediction[0]}') print('\033[1m{0:10}: {1:10}\033[0m\n-----------------------------------------------------------------------\n\n'.format('Confidence', confidence))