asteroid package

class asteroid.ConvTasNet(n_src, out_chan=None, n_blocks=8, n_repeats=3, bn_chan=128, hid_chan=512, skip_chan=128, conv_kernel_size=3, norm_type='gLN', mask_act='sigmoid', in_chan=None, fb_name='free', kernel_size=16, n_filters=512, stride=8, encoder_activation='relu', **fb_kwargs)

Bases: asteroid.models.base_models.BaseTasNet

ConvTasNet separation model, as described in [1].

Parameters:

• n_src (int) – Number of sources in the input mixtures.
• out_chan (int, optional) – Number of bins in the estimated masks. If None, out_chan = in_chan.
• n_blocks (int, optional) – Number of convolutional blocks in each repeat. Defaults to 8.
• n_repeats (int, optional) – Number of repeats. Defaults to 3.
• bn_chan (int, optional) – Number of channels after the bottleneck.
• hid_chan (int, optional) – Number of channels in the convolutional blocks.
• skip_chan (int, optional) – Number of channels in the skip connections. If 0 or None, TDConvNet won’t have any skip connections and the masks will be computed from the residual output. Corresponds to the ConvTasnet architecture in v1 or the paper.
• conv_kernel_size (int, optional) – Kernel size in convolutional blocks.
• norm_type (str, optional) – To choose from 'BN', 'gLN', 'cLN'.
• mask_act (str, optional) – Which non-linear function to generate mask.
• in_chan (int, optional) – Number of input channels, should be equal to n_filters.
• fb_name (str, className) – Filterbank family from which to make encoder and decoder. To choose among ['free', 'analytic_free', 'param_sinc', 'stft'].
• n_filters (int) – Number of filters / Input dimension of the masker net.
• kernel_size (int) – Length of the filters.
• stride (int, optional) – Stride of the convolution. If None (default), set to kernel_size // 2.
• **fb_kwargs (dict) – Additional kwards to pass to the filterbank creation.

References

[1] : “Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation” TASLP 2019 Yi Luo, Nima Mesgarani https://arxiv.org/abs/1809.07454

class asteroid.DPRNNTasNet(n_src, out_chan=None, bn_chan=128, hid_size=128, chunk_size=100, hop_size=None, n_repeats=6, norm_type='gLN', mask_act='sigmoid', bidirectional=True, rnn_type='LSTM', num_layers=1, dropout=0, in_chan=None, fb_name='free', kernel_size=16, n_filters=64, stride=8, encoder_activation='relu', **fb_kwargs)

Bases: asteroid.models.base_models.BaseTasNet

DPRNN separation model, as described in [1].

Parameters:

• n_src (int) – Number of masks to estimate.
• out_chan (int or None) – Number of bins in the estimated masks. Defaults to in_chan.
• bn_chan (int) – Number of channels after the bottleneck. Defaults to 128.
• hid_size (int) – Number of neurons in the RNNs cell state. Defaults to 128.
• chunk_size (int) – window size of overlap and add processing. Defaults to 100.
• hop_size (int or None) – hop size (stride) of overlap and add processing. Default to chunk_size // 2 (50% overlap).
• n_repeats (int) – Number of repeats. Defaults to 6.
• norm_type (str, optional) –

  Type of normalization to use. To choose from

  • 'gLN': global Layernorm
  • 'cLN': channelwise Layernorm
• mask_act (str, optional) – Which non-linear function to generate mask.
• bidirectional (bool, optional) – True for bidirectional Inter-Chunk RNN (Intra-Chunk is always bidirectional).
• rnn_type (str, optional) – Type of RNN used. Choose between 'RNN', 'LSTM' and 'GRU'.
• num_layers (int, optional) – Number of layers in each RNN.
• dropout (float, optional) – Dropout ratio, must be in [0,1].
• in_chan (int, optional) – Number of input channels, should be equal to n_filters.
• fb_name (str, className) – Filterbank family from which to make encoder and decoder. To choose among ['free', 'analytic_free', 'param_sinc', 'stft'].
• n_filters (int) – Number of filters / Input dimension of the masker net.
• kernel_size (int) – Length of the filters.
• stride (int, optional) – Stride of the convolution. If None (default), set to kernel_size // 2.
• **fb_kwargs (dict) – Additional kwards to pass to the filterbank creation.

References

[1] “Dual-path RNN: efficient long sequence modeling for

time-domain single-channel speech separation”, Yi Luo, Zhuo Chen and Takuya Yoshioka. https://arxiv.org/abs/1910.06379

class asteroid.DPTNet(n_src, ff_hid=256, chunk_size=100, hop_size=None, n_repeats=6, norm_type='gLN', ff_activation='relu', encoder_activation='relu', mask_act='relu', bidirectional=True, dropout=0, in_chan=None, fb_name='free', kernel_size=16, n_filters=64, stride=8, **fb_kwargs)

Bases: asteroid.models.base_models.BaseTasNet

DPTNet separation model, as described in [1].

Parameters:

• n_src (int) – Number of masks to estimate.
• out_chan (int or None) – Number of bins in the estimated masks. Defaults to in_chan.
• bn_chan (int) – Number of channels after the bottleneck. Defaults to 128.
• hid_size (int) – Number of neurons in the RNNs cell state. Defaults to 128.
• chunk_size (int) – window size of overlap and add processing. Defaults to 100.
• hop_size (int or None) – hop size (stride) of overlap and add processing. Default to chunk_size // 2 (50% overlap).
• n_repeats (int) – Number of repeats. Defaults to 6.
• norm_type (str, optional) –

  Type of normalization to use. To choose from

  • 'gLN': global Layernorm
  • 'cLN': channelwise Layernorm
• mask_act (str, optional) – Which non-linear function to generate mask.
• bidirectional (bool, optional) – True for bidirectional Inter-Chunk RNN (Intra-Chunk is always bidirectional).
• rnn_type (str, optional) – Type of RNN used. Choose between 'RNN', 'LSTM' and 'GRU'.
• num_layers (int, optional) – Number of layers in each RNN.
• dropout (float, optional) – Dropout ratio, must be in [0,1].
• in_chan (int, optional) – Number of input channels, should be equal to n_filters.
• fb_name (str, className) – Filterbank family from which to make encoder and decoder. To choose among ['free', 'analytic_free', 'param_sinc', 'stft'].
• n_filters (int) – Number of filters / Input dimension of the masker net.
• kernel_size (int) – Length of the filters.
• stride (int, optional) – Stride of the convolution. If None (default), set to kernel_size // 2.
• **fb_kwargs (dict) – Additional kwards to pass to the filterbank creation.

References

[1]: Jingjing Chen et al. “Dual-Path Transformer Network: Direct

Context-Aware Modeling for End-to-End Monaural Speech Separation” Interspeech 2020.

class asteroid.LSTMTasNet(n_src, out_chan=None, rnn_type='lstm', n_layers=4, hid_size=512, dropout=0.3, mask_act='sigmoid', bidirectional=True, in_chan=None, fb_name='free', n_filters=64, kernel_size=16, stride=8, encoder_activation=None, **fb_kwargs)

Bases: asteroid.models.base_models.BaseTasNet

TasNet separation model, as described in [1].

Parameters:

• n_src (int) – Number of masks to estimate.
• out_chan (int or None) – Number of bins in the estimated masks. Defaults to in_chan.
• hid_size (int) – Number of neurons in the RNNs cell state. Defaults to 128.
• mask_act (str, optional) – Which non-linear function to generate mask.
• bidirectional (bool, optional) – True for bidirectional Inter-Chunk RNN (Intra-Chunk is always bidirectional).
• rnn_type (str, optional) – Type of RNN used. Choose between 'RNN', 'LSTM' and 'GRU'.
• n_layers (int, optional) – Number of layers in each RNN.
• dropout (float, optional) – Dropout ratio, must be in [0,1].
• in_chan (int, optional) – Number of input channels, should be equal to n_filters.
• fb_name (str, className) – Filterbank family from which to make encoder and decoder. To choose among ['free', 'analytic_free', 'param_sinc', 'stft'].
• n_filters (int) – Number of filters / Input dimension of the masker net.
• kernel_size (int) – Length of the filters.
• stride (int, optional) – Stride of the convolution. If None (default), set to kernel_size // 2.
• **fb_kwargs (dict) – Additional kwards to pass to the filterbank creation.

References

[1]: Yi Luo et al. “Real-time Single-channel Dereverberation and Separation

with Time-domain Audio Separation Network”, Interspeech 2018

class asteroid.DeMask(input_type='mag', output_type='mag', hidden_dims=[1024], dropout=0, activation='relu', mask_act='relu', norm_type='gLN', fb_type='stft', n_filters=512, stride=256, kernel_size=512, **fb_kwargs)

Bases: asteroid.models.base_models.BaseModel

Simple MLP model for surgical mask speech enhancement A transformed-domain masking approach is used. :param input_type: whether the magnitude spectrogram “mag” or both real imaginary parts “reim” are

passed as features to the masker network. Concatenation of “mag” and “reim” also can be used by using “cat”.

Parameters:

• output_type (str, optional) – whether the masker ouputs a mask for magnitude spectrogram “mag” or both real imaginary parts “reim”.
• hidden_dims (list, optional) – list of MLP hidden layer sizes.
• dropout (float, optional) – dropout probability.
• activation (str, optional) – type of activation used in hidden MLP layers.
• mask_act (str, optional) – Which non-linear function to generate mask.
• norm_type (str, optional) – To choose from 'BN', 'gLN', 'cLN'.
• fb_name (str) – type of analysis and synthesis filterbanks used, choose between [“stft”, “free”, “analytic_free”].
• n_filters (int) – number of filters in the analysis and synthesis filterbanks.
• stride (int) – filterbank filters stride.
• kernel_size (int) – length of filters in the filterbank.
• encoder_activation (str) –
• **fb_kwargs (dict) – Additional kwards to pass to the filterbank creation.

forward(wav)

get_model_args()

Arguments needed to re-instantiate the model.

asteroid.show_available_models()

Subpackages

• asteroid.data package
  • Submodules
    • asteroid.data.avspeech_dataset module
    • asteroid.data.dns_dataset module
    • asteroid.data.fuss_dataset module
    • asteroid.data.kinect_wsj module
    • asteroid.data.librimix_dataset module
    • asteroid.data.musdb18_dataset module
    • asteroid.data.sms_wsj_dataset module
    • asteroid.data.utils module
    • asteroid.data.wham_dataset module
    • asteroid.data.whamr_dataset module
    • asteroid.data.wsj0_mix module
• asteroid.dsp package
  • Submodules
    • asteroid.dsp.consistency module
    • asteroid.dsp.overlap_add module
• asteroid.engine package
  • Submodules
    • asteroid.engine.optimizers module
    • asteroid.engine.schedulers module
    • asteroid.engine.system module
• asteroid.filterbanks package
  • Submodules
    • asteroid.filterbanks.analytic_free_fb module
    • asteroid.filterbanks.enc_dec module
    • asteroid.filterbanks.free_fb module
    • asteroid.filterbanks.griffin_lim module
    • asteroid.filterbanks.multiphase_gammatone_fb module
    • asteroid.filterbanks.param_sinc_fb module
    • asteroid.filterbanks.stft_fb module
    • asteroid.filterbanks.transforms module
• asteroid.losses package
  • Submodules
    • asteroid.losses.cluster module
    • asteroid.losses.mse module
    • asteroid.losses.multi_scale_spectral module
    • asteroid.losses.pit_wrapper module
    • asteroid.losses.pmsqe module
    • asteroid.losses.sdr module
    • asteroid.losses.stoi module
• asteroid.masknn package
  • Submodules
    • asteroid.masknn._local module
    • asteroid.masknn.activations module
    • asteroid.masknn.attention module
    • asteroid.masknn.blocks module
    • asteroid.masknn.convolutional module
    • asteroid.masknn.norms module
    • asteroid.masknn.recurrent module
• asteroid.models package
  • Submodules
    • asteroid.models.base_models module
    • asteroid.models.conv_tasnet module
    • asteroid.models.demask module
    • asteroid.models.dprnn_tasnet module
    • asteroid.models.dptnet module
    • asteroid.models.lstm_tasnet module
    • asteroid.models.publisher module
    • asteroid.models.sudormrf module
    • asteroid.models.zenodo module
• asteroid.scripts package
  • Submodules
    • asteroid.scripts.asteroid_cli module
• asteroid.utils package
  • Submodules
    • asteroid.utils.deprecation_utils module
    • asteroid.utils.generic_utils module
    • asteroid.utils.hub_utils module
    • asteroid.utils.parser_utils module
    • asteroid.utils.test_utils module
    • asteroid.utils.torch_utils module

Submodules

• asteroid.metrics module