{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"

🦜 BirdCLEF

\n","metadata":{"papermill":{"duration":0.045169,"end_time":"2022-02-23T00:22:56.789485","exception":false,"start_time":"2022-02-23T00:22:56.744316","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"\n

LET'S UNDERSTAND AUDIO FEATURES

","metadata":{"papermill":{"duration":0.042942,"end_time":"2022-02-23T00:22:56.992942","exception":false,"start_time":"2022-02-23T00:22:56.950000","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"\n

Audio Feature Extraction

\n\n

Feature extraction is the process of highlighting the most discriminating and impactful features of a signal.This notebook will walk you through some important feature extractions in audio processing and you can extend it to many other types of features which will be suitable for your problem domain.The rest of the notebook is just an attempt of a biotechnology student to explain you whatever signal processing she was able to understand in the last few days.So,bear with me😛","metadata":{"papermill":{"duration":0.043215,"end_time":"2022-02-23T00:22:57.078589","exception":false,"start_time":"2022-02-23T00:22:57.035374","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"

The Three Main Types of Audio Features Extraction we will discuss:

\n 1.Time Domain
\n 2.Frequency Domain
\n 3.Spectrum-Based\n","metadata":{"papermill":{"duration":0.042771,"end_time":"2022-02-23T00:22:57.165432","exception":false,"start_time":"2022-02-23T00:22:57.122661","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Import The Libraries📚","metadata":{"papermill":{"duration":0.042728,"end_time":"2022-02-23T00:22:57.251221","exception":false,"start_time":"2022-02-23T00:22:57.208493","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import os\nimport pandas as pd\nimport torch\nimport torchaudio\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport plotly.express as px\nimport librosa\nimport librosa.display\nimport IPython.display as ipd\nimport sklearn\nimport warnings\nimport seaborn as sns\nwarnings.filterwarnings('ignore')","metadata":{"_kg_hide-output":true,"papermill":{"duration":5.334901,"end_time":"2022-02-23T00:23:02.629198","exception":false,"start_time":"2022-02-23T00:22:57.294297","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:49:43.475799Z","iopub.execute_input":"2023-03-22T08:49:43.476191Z","iopub.status.idle":"2023-03-22T08:49:43.486439Z","shell.execute_reply.started":"2023-03-22T08:49:43.476150Z","shell.execute_reply":"2023-03-22T08:49:43.485152Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# SEE THE DATA 🐔:","metadata":{"papermill":{"duration":0.043252,"end_time":"2022-02-23T00:23:02.715904","exception":false,"start_time":"2022-02-23T00:23:02.672652","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_csv=pd.read_csv('../input/birdclef-2023/train_metadata.csv')\ntrain_csv.head()","metadata":{"papermill":{"duration":0.617869,"end_time":"2022-02-23T00:23:03.379049","exception":false,"start_time":"2022-02-23T00:23:02.761180","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:49:47.298848Z","iopub.execute_input":"2023-03-22T08:49:47.299358Z","iopub.status.idle":"2023-03-22T08:49:47.367084Z","shell.execute_reply.started":"2023-03-22T08:49:47.299312Z","shell.execute_reply":"2023-03-22T08:49:47.365986Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_csv['primary_label'].unique()","metadata":{"execution":{"iopub.status.busy":"2023-03-22T08:52:36.991408Z","iopub.execute_input":"2023-03-22T08:52:36.991789Z","iopub.status.idle":"2023-03-22T08:52:37.001709Z","shell.execute_reply.started":"2023-03-22T08:52:36.991751Z","shell.execute_reply":"2023-03-22T08:52:37.000495Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"SAMPLE A FEW AUDIOS FROM THE TRAIN SET","metadata":{"papermill":{"duration":0.044033,"end_time":"2022-02-23T00:23:03.467238","exception":false,"start_time":"2022-02-23T00:23:03.423205","status":"completed"},"tags":[]}},{"cell_type":"code","source":"base_dir = '../input/birdclef-2023/train_audio'\ntrain_csv['full_path'] = base_dir+ '/' + train_csv['filename']\nastfly = train_csv[train_csv['primary_label'] == \"abethr1\"].sample(1, random_state = 33)['full_path'].values[0]\ncasvir = train_csv[train_csv['primary_label'] == 'wfbeat1'].sample(1, random_state = 33)['full_path'].values[0]\nsubfly = train_csv[train_csv['primary_label'] == \"sacibi2\"].sample(1, random_state = 33)['full_path'].values[0]\nwilfly = train_csv[train_csv['primary_label'] == 'ndcsun2'].sample(1, random_state = 33)['full_path'].values[0]\nverdin = train_csv[train_csv['primary_label'] == 'barswa'].sample(1, random_state = 33)['full_path'].values[0]\nsolsan = train_csv[train_csv['primary_label'] == 'hipbab1'].sample(1, random_state = 33)['full_path'].values[0]\nbirds= [\"astfly\", \"casvir\", \"subfly\", \"wilfly\", \"verdin\",'solsan']","metadata":{"papermill":{"duration":0.20054,"end_time":"2022-02-23T00:23:03.711823","exception":false,"start_time":"2022-02-23T00:23:03.511283","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:53:41.670062Z","iopub.execute_input":"2023-03-22T08:53:41.670471Z","iopub.status.idle":"2023-03-22T08:53:41.702181Z","shell.execute_reply.started":"2023-03-22T08:53:41.670436Z","shell.execute_reply":"2023-03-22T08:53:41.700331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n

PLAY A FEW OF OUR SAMPLES:

","metadata":{"papermill":{"duration":0.044289,"end_time":"2022-02-23T00:23:03.800199","exception":false,"start_time":"2022-02-23T00:23:03.755910","status":"completed"},"tags":[]}},{"cell_type":"code","source":"ipd.Audio(astfly)","metadata":{"papermill":{"duration":0.074292,"end_time":"2022-02-23T00:23:03.918449","exception":false,"start_time":"2022-02-23T00:23:03.844157","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:53:45.461988Z","iopub.execute_input":"2023-03-22T08:53:45.462427Z","iopub.status.idle":"2023-03-22T08:53:45.474871Z","shell.execute_reply.started":"2023-03-22T08:53:45.462388Z","shell.execute_reply":"2023-03-22T08:53:45.473372Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ipd.Audio(casvir)","metadata":{"papermill":{"duration":0.262656,"end_time":"2022-02-23T00:23:04.231828","exception":false,"start_time":"2022-02-23T00:23:03.969172","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:53:52.175584Z","iopub.execute_input":"2023-03-22T08:53:52.175995Z","iopub.status.idle":"2023-03-22T08:53:52.200223Z","shell.execute_reply.started":"2023-03-22T08:53:52.175958Z","shell.execute_reply":"2023-03-22T08:53:52.198849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ipd.Audio(subfly)","metadata":{"papermill":{"duration":0.249438,"end_time":"2022-02-23T00:23:04.627623","exception":false,"start_time":"2022-02-23T00:23:04.378185","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:53:55.339922Z","iopub.execute_input":"2023-03-22T08:53:55.340308Z","iopub.status.idle":"2023-03-22T08:53:55.354850Z","shell.execute_reply.started":"2023-03-22T08:53:55.340257Z","shell.execute_reply":"2023-03-22T08:53:55.353146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ipd.Audio(solsan)","metadata":{"papermill":{"duration":0.338009,"end_time":"2022-02-23T00:23:05.145902","exception":false,"start_time":"2022-02-23T00:23:04.807893","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:53:57.045555Z","iopub.execute_input":"2023-03-22T08:53:57.046482Z","iopub.status.idle":"2023-03-22T08:53:57.060746Z","shell.execute_reply.started":"2023-03-22T08:53:57.046441Z","shell.execute_reply":"2023-03-22T08:53:57.059370Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Loading and Visualizing an audio file:\n* librosa.load: loads an audio file as a floating point time series and gives it's native sampling rate.\n* The sampling frequency (or sample rate) is the number of samples (data points) per second in an audio.\n* We can check the audio length by dividing the total number of data points by the sampling frequency.\n","metadata":{"papermill":{"duration":0.246518,"end_time":"2022-02-23T00:23:05.646370","exception":false,"start_time":"2022-02-23T00:23:05.399852","status":"completed"},"tags":[]}},{"cell_type":"code","source":"y, sr = librosa.load(subfly)\nprint('y:', y, '\\n')\nprint('y shape:', np.shape(y), '\\n')\nprint('Sample Rate (KHz):', sr, '\\n')\nprint('Check Len of Audio:', np.shape(y)[0]/sr)","metadata":{"papermill":{"duration":4.18762,"end_time":"2022-02-23T00:23:10.086537","exception":false,"start_time":"2022-02-23T00:23:05.898917","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:54:00.137676Z","iopub.execute_input":"2023-03-22T08:54:00.138065Z","iopub.status.idle":"2023-03-22T08:54:00.159193Z","shell.execute_reply.started":"2023-03-22T08:54:00.138029Z","shell.execute_reply":"2023-03-22T08:54:00.158037Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n

TRIMMING THE LEADING AND TRAILING SILENCE:🎵

","metadata":{"papermill":{"duration":0.247236,"end_time":"2022-02-23T00:23:10.586962","exception":false,"start_time":"2022-02-23T00:23:10.339726","status":"completed"},"tags":[]}},{"cell_type":"code","source":"audio_file, _ = librosa.effects.trim(y)\nprint('Audio File:', audio_file, '\\n')\nprint('Audio File shape:', np.shape(audio_file))","metadata":{"papermill":{"duration":0.301912,"end_time":"2022-02-23T00:23:11.138341","exception":false,"start_time":"2022-02-23T00:23:10.836429","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:54:02.052938Z","iopub.execute_input":"2023-03-22T08:54:02.053595Z","iopub.status.idle":"2023-03-22T08:54:02.073137Z","shell.execute_reply.started":"2023-03-22T08:54:02.053556Z","shell.execute_reply":"2023-03-22T08:54:02.071230Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n

APPLY TO ALL OUR SAMPLES:

","metadata":{"papermill":{"duration":0.243337,"end_time":"2022-02-23T00:23:11.632669","exception":false,"start_time":"2022-02-23T00:23:11.389332","status":"completed"},"tags":[]}},{"cell_type":"code","source":"y_astfly, sr_astfly = librosa.load(astfly)\naudio_astfly, _ = librosa.effects.trim(y_astfly)\n\ny_casvir, sr_casvir = librosa.load(casvir)\naudio_casvir, _ = librosa.effects.trim(y_casvir)\n\ny_subfly, sr_subfly = librosa.load(subfly)\naudio_subfly, _ = librosa.effects.trim(y_subfly)\n\ny_wilfly, sr_wilfly = librosa.load(wilfly)\naudio_wilfly, _ = librosa.effects.trim(y_wilfly)\n\ny_verdin, sr_verdin = librosa.load(verdin)\naudio_verdin, _ = librosa.effects.trim(y_verdin)\n\ny_solsan, sr_solsan = librosa.load(solsan)\naudio_solsan, _ = librosa.effects.trim(y_solsan)","metadata":{"_kg_hide-input":true,"papermill":{"duration":20.957854,"end_time":"2022-02-23T00:23:32.840524","exception":false,"start_time":"2022-02-23T00:23:11.882670","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:54:03.772744Z","iopub.execute_input":"2023-03-22T08:54:03.773320Z","iopub.status.idle":"2023-03-22T08:54:04.137003Z","shell.execute_reply.started":"2023-03-22T08:54:03.773231Z","shell.execute_reply":"2023-03-22T08:54:04.135312Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n

1.Time Domain Features

","metadata":{"papermill":{"duration":0.241177,"end_time":"2022-02-23T00:23:33.335146","exception":false,"start_time":"2022-02-23T00:23:33.093969","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"

Waveform Visualization

\n\n

To visualize the sampled signal and plot it, we need two Python libraries—Matplotlib and Librosa. The following code depicts the waveform visualization of the amplitude vs the time representation of the 6 signals.

","metadata":{"papermill":{"duration":0.237455,"end_time":"2022-02-23T00:23:33.810313","exception":false,"start_time":"2022-02-23T00:23:33.572858","status":"completed"},"tags":[]}},{"cell_type":"code","source":"fig, ax = plt.subplots(6, figsize = (16, 12))\nfig.suptitle('Sound Waves', fontsize=16)\n\nlibrosa.display.waveshow(y = audio_astfly, sr = sr_astfly, color = \"#A300F9\", ax=ax[0])\nlibrosa.display.waveshow(y = audio_casvir, sr = sr_casvir, color = \"#4300FF\", ax=ax[1])\nlibrosa.display.waveshow(y = audio_subfly, sr = sr_subfly, color = \"#009DFF\", ax=ax[2])\nlibrosa.display.waveshow(y = audio_wilfly, sr = sr_wilfly, color = \"#00FFB0\", ax=ax[3])\nlibrosa.display.waveshow(y = audio_verdin, sr = sr_verdin, color = \"#D9FF00\", ax=ax[4])\nlibrosa.display.waveshow(y = audio_solsan, sr = sr_solsan, color = \"r\", ax=ax[5]);\n\nfor i, name in zip(range(6), birds):\n ax[i].set_ylabel(name, fontsize=13)","metadata":{"_kg_hide-input":true,"papermill":{"duration":2.335792,"end_time":"2022-02-23T00:23:36.395456","exception":false,"start_time":"2022-02-23T00:23:34.059664","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:54:34.465240Z","iopub.execute_input":"2023-03-22T08:54:34.465643Z","iopub.status.idle":"2023-03-22T08:54:37.945652Z","shell.execute_reply.started":"2023-03-22T08:54:34.465603Z","shell.execute_reply":"2023-03-22T08:54:37.944340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

SPECTROGRAM

\n\n

A spectrogram is a visual representation of the spectrum of frequencies of a signal as it varies with time. They are time-frequency portraits of signals. Using a spectrogram, we can see how energy levels (dB) vary over time.It is a visual way of representing the signal strength, or “loudness”, of a signal over time at various frequencies present in a particular waveform.A spectrogram is usually depicted as a heat map, i.e., as an image with the intensity shown by varying the color or brightness.

\n-stft() converts data into short term Fourier transform. STFT converts signals such that we can know the amplitude of the given frequency at a given time. Using STFT we can determine the amplitude of various frequencies playing at a given time of an audio signal.
\n- .specshow is used to display a spectrogram.

\n \nThe Short-time Fourier transform (STFT), is a Fourier-related transform used to determine the sinusoidal frequency and phase content of local sections of a signal as it changes over time. In practice, the procedure for computing STFTs is to divide a longer time signal into shorter segments of equal length and then compute the Fourier transform separately on each shorter segment. This reveals the Fourier spectrum on each shorter segment. One then usually plots the changing spectra as a function of time, known as a spectrogram

\nLog-frequency axis: Features can be obtained from a spectrogram by converting the linear frequency axis into a logarithmic axis. The resulting representation is also called a log-frequency spectrogram

","metadata":{"papermill":{"duration":0.24808,"end_time":"2022-02-23T00:23:36.894868","exception":false,"start_time":"2022-02-23T00:23:36.646788","status":"completed"},"tags":[]}},{"cell_type":"code","source":"n_fft=2048\nhop_length=512\n# Short-time Fourier transform (STFT)\nD_astfly = np.abs(librosa.stft(audio_astfly, n_fft = n_fft, hop_length = hop_length))\n# Convert an amplitude spectrogram to Decibels-scaled spectrogram.\nDB_astfly = librosa.amplitude_to_db(D_astfly, ref = np.max)\n# === PLOT ===\nfig, ax = plt.subplots(1, 1, figsize=(12, 6))\nfig.suptitle('Log Frequency Spectrogram', fontsize=16)\n# fig.delaxes(ax[1, 2])\nimg=librosa.display.specshow(DB_astfly, sr = sr_astfly, hop_length = hop_length, x_axis = 'time', \n y_axis = 'log', cmap = 'cool', ax=ax)\nax.set_title('ASTFLY', fontsize=13) \nplt.colorbar(img,ax=ax)","metadata":{"_kg_hide-input":false,"papermill":{"duration":0.911368,"end_time":"2022-02-23T00:23:38.062410","exception":false,"start_time":"2022-02-23T00:23:37.151042","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:54:45.126502Z","iopub.execute_input":"2023-03-22T08:54:45.126878Z","iopub.status.idle":"2023-03-22T08:54:47.205611Z","shell.execute_reply.started":"2023-03-22T08:54:45.126845Z","shell.execute_reply":"2023-03-22T08:54:47.204393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

RMSE

\n\n

The energy of a signal corresponds to its total magnitude. For audio signals this roughly characterizes how loud the signal is.RMSE,a method of characterizing signal energy, calculates the square root of the mean square (the average of the squares of magnitude of the audio frames).\n

\nUsing a spectrogram can give us a more accurate representation of energy because its frames can be windowed. Therefore, if a spectrogram is already available, we prefer to run the RMS function over it

","metadata":{"papermill":{"duration":0.242016,"end_time":"2022-02-23T00:23:38.556775","exception":false,"start_time":"2022-02-23T00:23:38.314759","status":"completed"},"tags":[]}},{"cell_type":"code","source":"S, phase = librosa.magphase(librosa.stft(audio_astfly))\nS_db=librosa.amplitude_to_db(S, ref=np.max)\nrms = librosa.feature.rms(S=S)\nfig, ax = plt.subplots(nrows=2, sharex=True,figsize = (16, 6))\ntimes = librosa.times_like(rms)\nax[0].semilogy(times, rms[0], label='RMS Energy')\nax[0].set(xticks=[])\nax[0].legend()\nax[0].label_outer()\nlibrosa.display.specshow(S_db,\n y_axis='log', x_axis='time', ax=ax[1])\nax[1].set(title='log Power spectrogram')\nplt.show()","metadata":{"papermill":{"duration":1.4207,"end_time":"2022-02-23T00:23:40.224255","exception":false,"start_time":"2022-02-23T00:23:38.803555","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:54:50.098501Z","iopub.execute_input":"2023-03-22T08:54:50.100171Z","iopub.status.idle":"2023-03-22T08:54:51.667937Z","shell.execute_reply.started":"2023-03-22T08:54:50.100100Z","shell.execute_reply":"2023-03-22T08:54:51.666449Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

ZERO CROSSING RATE(ZCR)

\n\n

The ZCR of an audio signal is defined as the rate at which the signal changes sign. ZCR is an efficient and simple way to detecting whether a speech frame is voice, unvoiced, or silent. It is expected that unvoiced segments produce higher ZCRs than for voice segments, and ideally ZCRs equal to zero for silence segments \n

","metadata":{"papermill":{"duration":0.26499,"end_time":"2022-02-23T00:23:42.774402","exception":false,"start_time":"2022-02-23T00:23:42.509412","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"![1_jVwrBFZpXh6KLN_Uv5APfg.png](attachment:c7bb127c-f514-492a-a384-87578e67b68f.png)","metadata":{"papermill":{"duration":0.263712,"end_time":"2022-02-23T00:23:43.304564","exception":false,"start_time":"2022-02-23T00:23:43.040852","status":"completed"},"tags":[]},"attachments":{"c7bb127c-f514-492a-a384-87578e67b68f.png":{"image/png":"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"}}},{"cell_type":"code","source":"# Total zero_crossings in our 1 song\nzero_astfly = librosa.zero_crossings(audio_astfly, pad=False)\nzero_casvir = librosa.zero_crossings(audio_casvir, pad=False)\nzero_wilfly = librosa.zero_crossings(audio_wilfly, pad=False)\nzero_subfly = librosa.zero_crossings(audio_subfly, pad=False)\nzero_verdin = librosa.zero_crossings(audio_verdin, pad=False)\nzero_solsan = librosa.zero_crossings(audio_solsan, pad=False)\nzero_birds_list = [zero_astfly, zero_casvir, zero_wilfly, zero_subfly, zero_verdin,zero_solsan]\n\nfor bird, name in zip(zero_birds_list, birds):\n print(\"{} change rate is {:,}\".format(name, sum(bird)))","metadata":{"papermill":{"duration":53.277994,"end_time":"2022-02-23T00:24:36.845044","exception":false,"start_time":"2022-02-23T00:23:43.567050","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:55:05.295121Z","iopub.execute_input":"2023-03-22T08:55:05.295686Z","iopub.status.idle":"2023-03-22T08:55:10.322604Z","shell.execute_reply.started":"2023-03-22T08:55:05.295632Z","shell.execute_reply":"2023-03-22T08:55:10.320911Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Separation of Harmonic & Percussive Signals

\n\n

Sounds can broadly be classified into two classes.
-Harmonic sound on the one hand side is what we perceive as pitched sound and what makes us hear melodies and chords.
-Percussive sound on the other hand is noise-like and usually stems from instrument onsets like the hit on a drum or from consonants in speech.
\nhpss is harmonic-percussive source separation algorithm","metadata":{"papermill":{"duration":0.253601,"end_time":"2022-02-23T00:24:37.351732","exception":false,"start_time":"2022-02-23T00:24:37.098131","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"![download (7).jpg](attachment:c4006ba9-defc-41fb-a104-c2d5ba35aba0.jpg)","metadata":{"papermill":{"duration":0.265794,"end_time":"2022-02-23T00:24:37.880098","exception":false,"start_time":"2022-02-23T00:24:37.614304","status":"completed"},"tags":[]},"attachments":{"c4006ba9-defc-41fb-a104-c2d5ba35aba0.jpg":{"image/jpeg":"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"}}},{"cell_type":"code","source":"y_harm_casvir, y_perc_casvir = librosa.effects.hpss(audio_casvir)\nD_casvir = np.abs(librosa.stft(audio_casvir, n_fft = n_fft, hop_length = hop_length))\nDB_casvir = librosa.amplitude_to_db(D_casvir, ref = np.max)\nplt.figure(figsize = (16, 6))\nplt.plot(y_perc_casvir, color = '#FFB100')\nplt.plot(y_harm_casvir, color = '#A300F9')\nplt.legend((\"Perceptrual\", \"Harmonics\"))\nplt.title(\"Harmonics + Percussive : Casvir Bird\", fontsize=16);\n\n\nH, P = librosa.decompose.hpss(librosa.stft(audio_casvir)) \nplt.figure(figsize=(16, 6))\nplt.subplot(3, 1, 1)\nlibrosa.display.specshow(DB_casvir, y_axis='log')\nplt.colorbar(format='%+2.0f dB')\nplt.title('Full power spectrogram: Harmonic + Percussive')\n\n# harmonic spectrogram will show more horizontal/pitch-dependent changes\nplt.subplot(3, 1, 2)\nlibrosa.display.specshow(librosa.amplitude_to_db(np.abs(H), ref=np.max), y_axis='log')\nplt.colorbar(format='%+2.0f dB')\nplt.title('Harmonic power spectrogram')\nplt.subplot(3, 1, 3)\n\n# percussive spectrogram will show more vertical/time-dependent changes\nlibrosa.display.specshow(librosa.amplitude_to_db(np.abs(P), ref=np.max), y_axis='log')\nplt.colorbar(format='%+2.0f dB')\nplt.title('Percussive power spectrogram')\nplt.tight_layout()\nplt.show()","metadata":{"_kg_hide-input":true,"papermill":{"duration":56.992334,"end_time":"2022-02-23T00:25:35.141041","exception":false,"start_time":"2022-02-23T00:24:38.148707","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:55:13.123840Z","iopub.execute_input":"2023-03-22T08:55:13.124224Z","iopub.status.idle":"2023-03-22T08:55:20.762523Z","shell.execute_reply.started":"2023-03-22T08:55:13.124191Z","shell.execute_reply":"2023-03-22T08:55:20.761429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

CHROMAGRAM

\n\n

Chroma features are a powerful representation of music audio in which we use a 12-element representation of spectral energy called a chroma vector where each of the 12 bins represeent the 12 equal-tempered pitch class of western-type music (semitone spacing).
A chroma feature or vector is typically a 12-element feature vector indicating how much energy of each pitch class, {C, C#, D, D#, E, …, B}, is present in the signal. In short, It provides a robust way to describe a similarity measure between music pieces.
The 12 bins are clearly visisble in the plots below.It can be computed from the logarithmic short-time Fourier transform of the input sound signal, also called a chromagra

","metadata":{"papermill":{"duration":0.510145,"end_time":"2022-02-23T00:25:48.751020","exception":false,"start_time":"2022-02-23T00:25:48.240875","status":"completed"},"tags":[]}},{"cell_type":"code","source":"chroma=librosa.feature.chroma_stft(y=audio_casvir, sr=sr_casvir)\nfig, ax = plt.subplots(1,figsize = (10, 5))\nimg = librosa.display.specshow(chroma, y_axis='chroma', x_axis='time', ax=ax)\nfig.colorbar(img, ax=ax)\nax.set(title='Chromagram')","metadata":{"papermill":{"duration":2.874883,"end_time":"2022-02-23T00:25:52.148649","exception":false,"start_time":"2022-02-23T00:25:49.273766","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:57:52.821570Z","iopub.execute_input":"2023-03-22T08:57:52.821972Z","iopub.status.idle":"2023-03-22T08:57:53.363324Z","shell.execute_reply.started":"2023-03-22T08:57:52.821935Z","shell.execute_reply":"2023-03-22T08:57:53.362131Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#using an energy(magnitude) spectrum\nS = np.abs(librosa.stft(audio_casvir))\nchroma = librosa.feature.chroma_stft(S=S, sr=sr_casvir)#applying the logarithmic fourier transform\nfig, ax = plt.subplots(1,figsize = (10, 5))\nimg = librosa.display.specshow(chroma, y_axis='chroma', x_axis='time', ax=ax)\nfig.colorbar(img, ax=ax)\nax.set(title='Chromagram')","metadata":{"papermill":{"duration":2.17728,"end_time":"2022-02-23T00:25:54.835137","exception":false,"start_time":"2022-02-23T00:25:52.657857","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:57:56.251452Z","iopub.execute_input":"2023-03-22T08:57:56.251854Z","iopub.status.idle":"2023-03-22T08:57:56.775556Z","shell.execute_reply.started":"2023-03-22T08:57:56.251806Z","shell.execute_reply":"2023-03-22T08:57:56.773641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n

Constant Q-transform (CQT)

\n

The constant-Q transform transforms a data series to the frequency domain. It is related to the Fourier transform.
In general, the transform is well suited to musical data and proves useful where frequencies span several octaves.It is more useful in the identification of instruments.
To compute a constant-Q spectrogram, will use the libROSA cqt function:

","metadata":{"papermill":{"duration":0.306713,"end_time":"2022-02-23T00:25:55.465839","exception":false,"start_time":"2022-02-23T00:25:55.159126","status":"completed"},"tags":[]}},{"cell_type":"code","source":"chroma_stft = librosa.feature.chroma_stft(y=audio_casvir, sr=sr_casvir)\nchroma_cq = librosa.feature.chroma_cqt(y=audio_casvir, sr=sr_casvir)\nfig, ax = plt.subplots(nrows=2, sharex=True, sharey=True,figsize = (10, 9))\nlibrosa.display.specshow(chroma_stft, y_axis='chroma', x_axis='time', ax=ax[0])\nax[0].set(title='chroma_stft')\nax[0].label_outer()\nimg = librosa.display.specshow(chroma_cq, y_axis='chroma', x_axis='time', ax=ax[1])\nax[1].set(title='chroma_cqt')\n# ax[1].label_outer()\n# img = librosa.display.specshow(chroma_cens, y_axis='chroma', x_axis='time', ax=ax[2])\n# ax[2].set(title='chroma_cens')\nfig.colorbar(img, ax=ax)","metadata":{"papermill":{"duration":6.86706,"end_time":"2022-02-23T00:26:02.638665","exception":false,"start_time":"2022-02-23T00:25:55.771605","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:57:59.469725Z","iopub.execute_input":"2023-03-22T08:57:59.470169Z","iopub.status.idle":"2023-03-22T08:58:00.724087Z","shell.execute_reply.started":"2023-03-22T08:57:59.470127Z","shell.execute_reply":"2023-03-22T08:58:00.723405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n\n

Chroma Energy distribution Normalized Statistics (CENS)

\n

Another chroma-based feature is chroma energy distribution normalized statistics (CENS) which is typically used to identify similarity between different interpretations of the music given.CENS are typically implemented for audio matching and similarity tasks.

","metadata":{"papermill":{"duration":0.310205,"end_time":"2022-02-23T00:26:03.268613","exception":false,"start_time":"2022-02-23T00:26:02.958408","status":"completed"},"tags":[]}},{"cell_type":"code","source":"chroma_stft = librosa.feature.chroma_stft(y=audio_casvir, sr=sr_casvir)\nchroma_cens = librosa.feature.chroma_cens(y=audio_casvir, sr=sr_casvir)\n\nfig, ax = plt.subplots(nrows=2, sharex=True, sharey=True,figsize = (10, 9))\nlibrosa.display.specshow(chroma_stft, y_axis='chroma', x_axis='time', ax=ax[0])\nax[0].set(title='chroma_stft')\nax[0].label_outer()\n\nimg = librosa.display.specshow(chroma_cens, y_axis='chroma', x_axis='time', ax=ax[1])\nax[1].set(title='chroma_cens')\nfig.colorbar(img, ax=ax)","metadata":{"papermill":{"duration":6.65226,"end_time":"2022-02-23T00:26:10.227533","exception":false,"start_time":"2022-02-23T00:26:03.575273","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T08:58:04.557618Z","iopub.execute_input":"2023-03-22T08:58:04.558021Z","iopub.status.idle":"2023-03-22T08:58:06.203878Z","shell.execute_reply.started":"2023-03-22T08:58:04.557983Z","shell.execute_reply":"2023-03-22T08:58:06.201879Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n

Spectrum Related Features

","metadata":{"papermill":{"duration":0.308583,"end_time":"2022-02-23T00:26:10.851190","exception":false,"start_time":"2022-02-23T00:26:10.542607","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"\n

SPECTRAL CONTRAST

\n\n

The difference between spectral peaks and spectral valleys will reflect the spectral contrast distribution.
Spectral peaks correspond to harmonic components and Spectral valleys correspond to non-harmonic components or noise in a music piece.It considers the spectral peak and valley in each sub-band separately.\n","metadata":{"papermill":{"duration":0.325527,"end_time":"2022-02-23T00:26:14.775449","exception":false,"start_time":"2022-02-23T00:26:14.449922","status":"completed"},"tags":[]}},{"cell_type":"code","source":"contrast = librosa.feature.spectral_contrast(y=y_harm_casvir,sr=sr_casvir)\nplt.figure(figsize=(15,5))\nlibrosa.display.specshow(contrast, x_axis='time')\nplt.colorbar()\nplt.ylabel('Frequency bands')\nplt.title('Spectral contrast')","metadata":{"papermill":{"duration":1.456562,"end_time":"2022-02-23T00:26:16.563083","exception":false,"start_time":"2022-02-23T00:26:15.106521","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T09:00:33.488938Z","iopub.execute_input":"2023-03-22T09:00:33.489450Z","iopub.status.idle":"2023-03-22T09:00:33.878518Z","shell.execute_reply.started":"2023-03-22T09:00:33.489409Z","shell.execute_reply":"2023-03-22T09:00:33.876752Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n\n\n

Mel-frequency cepstral coefficients (MFCCs)

\n\n

One popular audio feature extraction method is the Mel-frequency cepstral coefficients (MFCC), which has 39 features. The feature count is small enough to force the model to learn the information of the audio. 12 parameters are related to the amplitude of frequencies. It models the characteristics of the human voice. The extraction flow of MFCC features is depicted below:","metadata":{"papermill":{"duration":0.323219,"end_time":"2022-02-23T00:26:18.728690","exception":false,"start_time":"2022-02-23T00:26:18.405471","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"![1_M3Fq-ltf5dkLW85xc2T6YA.png](attachment:e34d5199-95a3-4c4c-ae38-9557e2ba9209.png)","metadata":{"papermill":{"duration":0.326947,"end_time":"2022-02-23T00:26:19.383427","exception":false,"start_time":"2022-02-23T00:26:19.056480","status":"completed"},"tags":[]},"attachments":{"e34d5199-95a3-4c4c-ae38-9557e2ba9209.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"

This feature is one of the most important method to extract a feature of an audio signal and is used majorly whenever working on audio signals. The mel frequency cepstral coefficients (MFCCs) of a signal are a small set of features (usually about 10–20) which concisely describe the overall shape of a spectral envelope.

By printing the shape of mfccs you get how many mfccs are calculated on how many frames. The first value represents the number of mfccs calculated and another value represents a number of frames available.\n","metadata":{"papermill":{"duration":0.322399,"end_time":"2022-02-23T00:26:20.029739","exception":false,"start_time":"2022-02-23T00:26:19.707340","status":"completed"},"tags":[]}},{"cell_type":"code","source":"mfcc=librosa.feature.mfcc(y=audio_astfly, sr=sr_astfly)\nfig, ax = plt.subplots(1,figsize = (12, 6))\nimg = librosa.display.specshow(mfcc, x_axis='time', ax=ax)\nprint(mfcc.shape)\nfig.colorbar(img, ax=ax)\nax.set(title='MFCC')","metadata":{"papermill":{"duration":0.647495,"end_time":"2022-02-23T00:26:21.002866","exception":false,"start_time":"2022-02-23T00:26:20.355371","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-03-22T09:00:55.597363Z","iopub.execute_input":"2023-03-22T09:00:55.597779Z","iopub.status.idle":"2023-03-22T09:00:56.005469Z","shell.execute_reply.started":"2023-03-22T09:00:55.597741Z","shell.execute_reply":"2023-03-22T09:00:56.004317Z"},"trusted":true},"execution_count":null,"outputs":[]}]}