.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "acoustic/acoustic_sig_aug_tutorial.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_acoustic_acoustic_sig_aug_tutorial.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_acoustic_acoustic_sig_aug_tutorial.py:


Acoustic Augmentation.Signal_aug Tutorial
==============================================================

.. GENERATED FROM PYTHON SOURCE LINES 7-8

!pip install pysensing

.. GENERATED FROM PYTHON SOURCE LINES 10-12

In this tutorial, we will be implementing a simple acoustic.augmentation.sig_aug


.. GENERATED FROM PYTHON SOURCE LINES 12-17

.. code-block:: Python

    import torch
    import torchaudio
    import matplotlib.pyplot as plt
    from pysensing.acoustic.augmentation import signal_aug
    from pysensing.acoustic.preprocessing import transform







.. GENERATED FROM PYTHON SOURCE LINES 18-21

Load the audio
-----------------------------------
First, the example audio is loaded

.. GENERATED FROM PYTHON SOURCE LINES 21-41

.. code-block:: Python


    # Define the plot function
    def plot(audio_data_list, titles,channel_first=True):
        num_audios = len(audio_data_list)
        fig, axes = plt.subplots(num_audios, 1, figsize=(12, 8))
        if num_audios == 1:
            axes = [axes]
        for ax, audio_data, title in zip(axes, audio_data_list, titles):
            if channel_first==False:
                ax.plot(audio_data.numpy())
            else:
                ax.plot(audio_data[0].numpy())
            ax.set_title(title)
        fig.tight_layout()
        plt.show()

    # Load the data
    # Load the data
    waveform, sample_rate = torchaudio.load('example_data/example_audio.wav')








.. GENERATED FROM PYTHON SOURCE LINES 42-44

1. Add Noise
------------------------

.. GENERATED FROM PYTHON SOURCE LINES 44-54

.. code-block:: Python


    noise = torch.randn_like(waveform)
    add_noise_0 = signal_aug.add_noise(noise,torch.tensor([0]))
    add_noise_5 = signal_aug.add_noise(noise,torch.tensor([20]))

    noise_data_0 = add_noise_0(waveform)
    noise_data_5 = add_noise_5(waveform)

    plot([waveform,noise_data_5,noise_data_0],['Original','SNR=20','SNR=0'])




.. image-sg:: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_001.png
   :alt: Original, SNR=20, SNR=0
   :srcset: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_001.png
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 55-57

2. Add echo
------------------------

.. GENERATED FROM PYTHON SOURCE LINES 57-63

.. code-block:: Python

    waveform, sample_rate = torchaudio.load('example_data/example_audio.wav',channels_first=False)
    add_echo_tran = signal_aug.add_echo(sample_rate,in_gain=0.6,out_gain=0.3,delays=[1000],decays=[0.5])
    echo_data = add_echo_tran(waveform)

    plot([waveform,echo_data],['Original','Add_echo'],False)




.. image-sg:: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_002.png
   :alt: Original, Add_echo
   :srcset: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_002.png
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 64-66

3. Add atempo
------------------------

.. GENERATED FROM PYTHON SOURCE LINES 66-72

.. code-block:: Python


    add_echo_tran = signal_aug.add_echo(sample_rate,in_gain=0.6,out_gain=0.3,delays=[1000],decays=[0.5])
    echo_data = add_echo_tran(waveform)

    plot([waveform,echo_data],['Original','Add_echo'],False)




.. image-sg:: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_003.png
   :alt: Original, Add_echo
   :srcset: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_003.png
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 73-75

4. Add chorus
------------------------

.. GENERATED FROM PYTHON SOURCE LINES 75-80

.. code-block:: Python


    add_chorus_trans = signal_aug.add_chorus(sample_rate,in_gain=0.6,out_gain=0.3,delays=[1000],decays=[0.5],speeds=[0.25],depths=[2.0])
    chorus_data        = add_chorus_trans(waveform)
    plot([waveform,chorus_data],['Original','Add_chorus'],False)




.. image-sg:: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_004.png
   :alt: Original, Add_chorus
   :srcset: /acoustic/images/sphx_glr_acoustic_sig_aug_tutorial_004.png
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 81-82

And that's it. We're done with our acoustic augmentation.signal_aug tutorials. Thanks for reading.


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 1.013 seconds)


.. _sphx_glr_download_acoustic_acoustic_sig_aug_tutorial.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: acoustic_sig_aug_tutorial.ipynb <acoustic_sig_aug_tutorial.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: acoustic_sig_aug_tutorial.py <acoustic_sig_aug_tutorial.py>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_