{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import soundfile as sf\nimport matplotlib.pyplot as plt\nfrom IPython.display import Audio\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"SAMPLE_ID = \"08dc46957\"\nSAMPLE_FILE = f\"../input/rfcx-species-audio-detection/train/{SAMPLE_ID}.flac\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"audio_signal, sampling_rate = sf.read(SAMPLE_FILE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sampling_rate","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(12, 8))\n\n\nax.set_title(\"Audio signal for {}\")\nax.plot(audio_signal)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Audio(SAMPLE_FILE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(20, 10))\n\n\nax.set_title(f\"Audio signal for {SAMPLE_ID}\")\nax.plot(audio_signal[:2000])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import librosa\nfrom librosa.display import specshow\nimport numpy as np\n\n\ntransformed_audio_signal = librosa.stft(audio_signal)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 3))\n\nS = librosa.feature.melspectrogram(y=audio_signal, sr=sampling_rate)\nS_dB = librosa.power_to_db(S, ref=np.max)\n\n\nimg = librosa.display.specshow(S_dB, x_axis='time', y_axis='mel', sr=sampling_rate,\n                               fmax=16000, ax=ax)\n\nfig.colorbar(img, ax=ax, format='%+2.0f dB')\n\nax.set(title='Mel-frequency spectrogram')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"S = librosa.feature.melspectrogram(y=audio_signal, sr=sampling_rate, n_mels=128, fmax=16000)\n\nmfccs = librosa.feature.mfcc(S=librosa.power_to_db(S))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 5))\n\n\nim = specshow(mfccs, x_axis='time', y_axis='mel', ax=ax, sr=48000,\n                             fmax=24000, fmin=40)\n\n\nfig.colorbar(im, format='%+2.0f dB')\n\n\nax.set_title(f'MFCC for {SAMPLE_ID}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def compute_and_plot_mfccs(sample_id=\"b24f28ef8\"):\n    sample_file = f\"../input/rfcx-species-audio-detection/train/{sample_id}.flac\"\n    audio_signal, sampling_rate = sf.read(sample_file)\n    S = librosa.feature.melspectrogram(y=audio_signal, sr=sampling_rate, n_mels=128,\n                                       fmax=16000) # 16k is better?\n\n    mfccs = librosa.feature.mfcc(S=librosa.power_to_db(S))\n    fig, ax = plt.subplots(figsize=(15, 5))\n\n\n    mfccs = librosa.feature.mfcc(S=librosa.power_to_db(S))\n\n    im = specshow(mfccs, x_axis='time', y_axis='mel', ax=ax, sr=48000,\n                                 fmax=24000, fmin=40)\n\n\n    fig.colorbar(im, format='%+2.0f dB')\n\n\n    ax.set_title(f'MFCC for {sample_id}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"compute_and_plot_mfccs()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(mfccs)","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}