Code

augmenter = Compose(
                [
                    RoomSimulator(
                        p=1.0,
                        leave_length_unchanged=True,
                    ),
                    AddBackgroundNoise(
                        sounds_path=os.path.join(random.choice(BACKGROUND_NOISE_FILES)),
                        min_snr_in_db=15,
                        max_snr_in_db=35,
                        p=1.0,
                    )
                ]
            )
            wave = augmenter(samples=wave, sample_rate=sample_rate)

Trace:

 File "/home/sk/anaconda3/envs/vc/lib/python3.8/site-packages/audiomentations/core/composition.py", line 88, in __call__
    samples = transform(samples, sample_rate)
  File "/home/sk/anaconda3/envs/vc/lib/python3.8/site-packages/audiomentations/core/transforms_interface.py", line 62, in __call__
    self.randomize_parameters(samples, sample_rate)
  File "/home/sk/anaconda3/envs/vc/lib/python3.8/site-packages/audiomentations/augmentations/room_simulator.py", line 339, in randomize_parameters
    self.room.compute_rir()
  File "/home/sk/anaconda3/envs/vc/lib/python3.8/site-packages/pyroomacoustics/room.py", line 2156, in compute_rir
    vis = self.visibility[s][m, :].astype(np.int32)
IndexError: list index out of range

It happens occasionally on specific wav files.

Currently audiomentations doesn't work with stereo audio. Most of transformations failed with:

librosa.util.exceptions.ParameterError: Invalid shape for monophonic audio: ndim=2, shape=(240000, 2)

One of possible workaround is to apply same transormations for each channel independently. But how to use the same transformations with same parameters?

[Draft]

This MR adds docs and their respective web objects in descending order.
Docs completed so far are:

• [x] Trim
• [x] Time stretch
• [ ] Time Mask
• [x] Tanh Distortion
• [ ] Shift
• [ ] Seven band parametric eq
• [ ] Room simulator
• [ ] Reverse
• [ ] Resample
• [ ] Polarity inversion
• [ ] Pitch Shift
• [ ] Peaking filter
• [ ] Padding
• [ ] Normalize
• [ ] mp3 compression
• [ ] Low shelf filter
• [ ] Low pass filter
• [ ] Loudness normalization
• [ ] Limiter
• [ ] Lambda
• [ ] High shelf filter
• [ ] High pass filter
• [ ] Gain
• [ ] Gain transition
• [ ] Clipping distortion
• [ ] Clip
• [ ] Band stop filter
• [ ] Band pass filter
• [ ] Apply impulse response
• [ ] Air absoption
• [ ] Add short noises
• [x] Add gaussian SNR
• [x] Add gaussian noise
• [x] Add background noise

I encountered this error, which caused by TimeMask

time mask: t0 138974  t: 21416  m.shpae: (21416,)  newshpae: (93184,)  rawshpae: (93184,)  slice shape: (0,)
err:  operands could not be broadcast together with shapes (0,) (21416,) (0,) 

augmenter = Compose([
        TimeStretch(min_rate=0.8, max_rate=1.25, p=1.0),
        AddGaussianNoise(min_amplitude=0.001, max_amplitude=0.015, p=0.2),
        PitchShift(min_semitones=-4, max_semitones=4, p=0.2),
        Shift(min_fraction=-0.5, max_fraction=0.5, p=0.2),
        FrequencyMask(min_frequency_band=0.0, max_frequency_band=0.5, p=0.2),
        TimeMask(min_band_part=0.0, max_band_part=0.5, fade=False, p=0.2)
], p=1.0, shuffle=False)

def aug_sample(samples, sample_rate):
  assert samples.dtype == np.int16 
  samples =  samples * max(0.01, np.max(np.abs(samples))) / 32768.0
  samples = samples.astype(np.float32)
  samples = augmenter(samples=samples, sample_rate=sample_rate)
  samples *= 32767 / max(0.01, np.max(np.abs(samples)))
  samples = samples.astype(np.int16)
  return samples

using aug_sample to load wav by threading.Thread like mapreduce.

I am trying to use Mp3Compression with backend="pydub". But having this NoBackendError below. Do you have any idea about the issue? Regards,

• Windows10
• python 3.8.5
• ffmpeg version = 4.3.1 (conda package)
• pydub version = 0.23.1 (conda package)

C:\Users\user\anaconda3\envs\ml\lib\site-packages\librosa\core\audio.py:162: UserWarning: PySoundFile failed. Trying audioread instead.
  warnings.warn("PySoundFile failed. Trying audioread instead.")
---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
~\anaconda3\envs\ml\lib\site-packages\librosa\core\audio.py in load(path, sr, mono, offset, duration, dtype, res_type)
    145     try:
--> 146         with sf.SoundFile(path) as sf_desc:
    147             sr_native = sf_desc.samplerate

~\anaconda3\envs\ml\lib\site-packages\soundfile.py in __init__(self, file, mode, samplerate, channels, subtype, endian, format, closefd)
    628                                          format, subtype, endian)
--> 629         self._file = self._open(file, mode_int, closefd)
    630         if set(mode).issuperset('r+') and self.seekable():

~\anaconda3\envs\ml\lib\site-packages\soundfile.py in _open(self, file, mode_int, closefd)
   1182             raise TypeError("Invalid file: {0!r}".format(self.name))
-> 1183         _error_check(_snd.sf_error(file_ptr),
   1184                      "Error opening {0!r}: ".format(self.name))

~\anaconda3\envs\ml\lib\site-packages\soundfile.py in _error_check(err, prefix)
   1356         err_str = _snd.sf_error_number(err)
-> 1357         raise RuntimeError(prefix + _ffi.string(err_str).decode('utf-8', 'replace'))
   1358 

RuntimeError: Error opening 'C:\\Users\\user\\AppData\\Local\\Temp\\tmp_compressed_37ed35fe-9a1.mp3': Format not recognised.

During handling of the above exception, another exception occurred:

NoBackendError                            Traceback (most recent call last)
<ipython-input-296-889e15591d71> in <module>
     25 ])
     26 
---> 27 augmented_data = augment(samples=data.T[0], sample_rate=SAMPLE_RATE)
     28 
     29 plt.plot(augmented_data)

~\anaconda3\envs\ml\lib\site-packages\audiomentations\core\composition.py in __call__(self, samples, sample_rate)
     50                 random.shuffle(transforms)
     51             for transform in transforms:
---> 52                 samples = transform(samples, sample_rate)
     53 
     54         return samples

~\anaconda3\envs\ml\lib\site-packages\audiomentations\core\transforms_interface.py in __call__(self, samples, sample_rate)
     74                     )
     75                 )
---> 76             return self.apply(samples, sample_rate)
     77         return samples
     78 

~\anaconda3\envs\ml\lib\site-packages\audiomentations\augmentations\transforms.py in apply(self, samples, sample_rate)
   1054             return self.apply_lameenc(samples, sample_rate)
   1055         elif self.backend == "pydub":
-> 1056             return self.apply_pydub(samples, sample_rate)
   1057         else:
   1058             raise Exception("Backend {} not recognized".format(self.backend))

~\anaconda3\envs\ml\lib\site-packages\audiomentations\augmentations\transforms.py in apply_pydub(self, samples, sample_rate)
   1134         file_handle.close()
   1135 
-> 1136         degraded_samples, _ = librosa.load(tmp_file_path, sample_rate)
   1137 
   1138         os.unlink(tmp_file_path)

~\anaconda3\envs\ml\lib\site-packages\librosa\core\audio.py in load(path, sr, mono, offset, duration, dtype, res_type)
    161         if isinstance(path, (str, pathlib.PurePath)):
    162             warnings.warn("PySoundFile failed. Trying audioread instead.")
--> 163             y, sr_native = __audioread_load(path, offset, duration, dtype)
    164         else:
    165             raise (exc)

~\anaconda3\envs\ml\lib\site-packages\librosa\core\audio.py in __audioread_load(path, offset, duration, dtype)
    185 
    186     y = []
--> 187     with audioread.audio_open(path) as input_file:
    188         sr_native = input_file.samplerate
    189         n_channels = input_file.channels

~\anaconda3\envs\ml\lib\site-packages\audioread\__init__.py in audio_open(path, backends)
    114 
    115     # All backends failed!
--> 116     raise NoBackendError()

NoBackendError: 

Implementing https://github.com/iver56/audiomentations/issues/7, https://github.com/iver56/audiomentations/issues/8 and https://github.com/iver56/audiomentations/issues/9.

• [x] Adopt this approach: https://github.com/asteroid-team/torch-audiomentations/blob/master/torch_audiomentations/augmentations/band_pass_filter.py#L18

Hello,

I just wrote a function, for ECG augmentation. The main purpose is simulate the signals when the ECG electrodes are in lead-off condition. It can also be used for audio data augmentation. The function generates random number of flat pulses with some noise on it. The pulses' amplitudes are between signal max-min range and pulses have random width. Maybe the function can be added here.

Regards,

import wavio
import numpy as np
from matplotlib import pyplot as plt

audio_seg=wavio.read("sample_audio.wav").data.astype(np.float32).T[0]

def InterruptSignal(audio_seg, max_num_interruptions, noise_level, p):
    # audio_seg:             Audio segment (1D Numpy array)
    # max_num_interruptions: Maximum number of interruption pulses. Pulses are generated randomly
    # noise_level:           The level of noise to be added the pulses. "CNN's don't like constant values :)"
    # p:                     Triggering probability
    if np.random.random() < p / 1.:
        max_peak = np.max(audio_seg).astype(int)
        min_peak = np.min(audio_seg).astype(int)
        len_audio                = audio_seg.shape[-1]
        num_random_interruptions = np.random.randint(max_num_interruptions)+1
        interruption_start_times = (len_audio * np.random.random(num_random_interruptions)*4/5).astype(int)
        for interruption in interruption_start_times:
            interruption_len = int(len_audio*np.random.random()//5)
            interruption_val = np.random.randint(min_peak, max_peak)
            audio_seg[interruption:interruption+interruption_len] = interruption_val+np.random.normal(0, 1, interruption_len)*noise_level
    return audio_seg

fig, (ax1, ax2) = plt.subplots(2)
fig.suptitle('Two random interruptions with some noise')
ax1.plot(audio_seg[:5000])
ax2.plot(InterruptSignal(audio_seg[:5000],
                         max_num_interruptions=3,
                         noise_level=100,
                         p=1))
plt.show()

Implements https://github.com/iver56/audiomentations/issues/176, except from unittest.mock in test_room_simulator.py. I can replace it with pytest-mock if necessary.

When I use AddBackgroundNoise method, most of the time I got following error: MultichannelAudioNotSupportedException: AddBackgroundNoise only supports mono audio, not multichannel audio But the noise folder which I have pointed has 16kHz, 16bit PCM(little/signed), 1 channel wav files in it.

When I run CircleCI check on my forked repo, I've got this message:

"You’re using a deprecated Docker convenience image. Upgrade to a next-gen Docker convenience image."

Does this need to be fixed by changing .circleci/config.yml, or it can be left as it is for now?

Should have a target duration parameter that can be specified either in seconds or in number of samples

If the input sound is longer than the target duration, pick a random offset (so we don't always output just the beginning of the audio) and crop the sound to the target duration

If the input sound is shorter than the target duration, pad the end of the sound (append digital silence) so the duration matches the target duration. Maybe it makes sense to support various padding modes here, just like in the Padding transform.

Audio transmitted via bluetooth can sometimes be compressed with LC3. Let's make a transform that simulates this lossy audio encoding.

https://github.com/google/liblc3

• Deprecate (and later remove) min_amplitude and max_amplitude in AddGaussianNoise
• Add min_snr_in_db, max_snr_in_db, min_absolute_rms_db, max_absolute_rms_db and mode
• Deprecate (and later remove) AddGaussianSNR

I feel like it isn't limited to adding specifically background noise - it could be any type of noise or actually any audio (it doesn't have to be noise although that is a common thing to do)

Any suggestions for a better name? AddNoise? AddNoiseFromFiles? MixInSoundFile?