DSP Modules¶

Beamforming¶

class asteroid.dsp.beamforming.MvdrBeamformer(*args, **kwargs)[source]¶

Bases: asteroid.dsp.beamforming.BeamFormer

forward(mix: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62af3e50>, target_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62af3810>, noise_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62af3b90>)[source]¶

Compute and apply MVDR beamformer from the speech and noise SCM matrices.

$\mathbf{w} = \displaystyle \frac{\Sigma_{nn}^{-1} \mathbf{a}}{ \mathbf{a}^H \Sigma_{nn}^{-1} \mathbf{a}}$ where $\mathbf{a}$ is the ATF estimated from the target SCM.

Parameters:	mix (torch.ComplexTensor) – shape (batch, mics, freqs, frames) target_scm (torch.ComplexTensor) – (batch, mics, mics, freqs) noise_scm (torch.ComplexTensor) – (batch, mics, mics, freqs)
Returns:	Filtered mixture. torch.ComplexTensor (batch, freqs, frames)

from_atf_vect(mix: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acfd10>, atf_vec: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acffd0>, noise_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acfad0>)[source]¶

Compute and apply MVDR beamformer from the ATF vector and noise SCM matrix.

Parameters:	mix (torch.ComplexTensor) – shape (batch, mics, freqs, frames) atf_vec (torch.ComplexTensor) – (batch, mics, freqs) noise_scm (torch.ComplexTensor) – (batch, mics, mics, freqs)
Returns:	Filtered mixture. torch.ComplexTensor (batch, freqs, frames)

class asteroid.dsp.beamforming.SdwMwfBeamformer(mu=1.0)[source]¶

Bases: asteroid.dsp.beamforming.BeamFormer

forward(mix: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acf510>, target_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acfb10>, noise_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acfb90>, ref_mic: int = 0)[source]¶

Compute and apply SDW-MWF beamformer.

$\mathbf{w} = \displaystyle (\Sigma_{ss} + \mu \Sigma_{nn})^{-1} \Sigma_{ss}$.

Parameters:	mix (torch.ComplexTensor) – shape (batch, mics, freqs, frames) target_scm (torch.ComplexTensor) – (batch, mics, mics, freqs) noise_scm (torch.ComplexTensor) – (batch, mics, mics, freqs) ref_mic (int) – reference microphone.
Returns:	Filtered mixture. torch.ComplexTensor (batch, freqs, frames)

class asteroid.dsp.beamforming.GEVBeamformer(*args, **kwargs)[source]¶

Bases: asteroid.dsp.beamforming.BeamFormer

forward(mix: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acfa90>, target_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acf6d0>, noise_scm: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62acf410>)[source]¶

Compute and apply the GEV beamformer.

$\mathbf{w} = \displaystyle MaxEig\{ \Sigma_{nn}^{-1}\Sigma_{ss} \}$, where MaxEig extracts the eigenvector corresponding to the maximum eigenvalue (using the GEV decomposition).

Parameters:	mix – shape (batch, mics, freqs, frames) target_scm – (batch, mics, mics, freqs) noise_scm – (batch, mics, mics, freqs)
Returns:	Filtered mixture. torch.ComplexTensor (batch, freqs, frames)

class asteroid.dsp.beamforming.SCM(*args, **kwargs)[source]¶

Bases: sphinx.ext.autodoc.importer._MockObject

forward(x: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62af3b50>, mask: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f62af3090> = None, normalize: bool = True)[source]¶: See compute_scm().

LambdaOverlapAdd¶

class asteroid.dsp.LambdaOverlapAdd(nnet, n_src, window_size, hop_size=None, window='hanning', reorder_chunks=True, enable_grad=False)[source]¶

Bases: sphinx.ext.autodoc.importer._MockObject

Overlap-add with lambda transform on segments (not scriptable).

Segment input signal, apply lambda function (a neural network for example) and combine with OLA.

LambdaOverlapAdd can be used with asteroid.separate and the asteroid-infer CLI.

Parameters:

nnet (callable) – Function to apply to each segment.
n_src (Optional[int]) – Number of sources in the output of nnet. If None, the number of sources is determined by the network’s output, but some correctness checks cannot be performed.
window_size (int) – Size of segmenting window.
hop_size (int) – Segmentation hop size.
window (str) – Name of the window (see scipy.signal.get_window) used for the synthesis.
reorder_chunks – Whether to reorder each consecutive segment. This might be useful when nnet is permutation invariant, as source assignements might change output channel from one segment to the next (in classic speech separation for example). Reordering is performed based on the correlation between the overlapped part of consecutive segment.

ola_forward(x)[source]¶: Heart of the class: segment signal, apply func, combine with OLA.

forward(x)[source]¶

Forward module: segment signal, apply func, combine with OLA.

Parameters:	x (`torch.Tensor`) – waveform signal of shape (batch, 1, time).
Returns:	`torch.Tensor` – The output of the lambda OLA.

DualPath Processing¶

class asteroid.dsp.DualPathProcessing(chunk_size, hop_size)[source]¶

Bases: sphinx.ext.autodoc.importer._MockObject

Perform Dual-Path processing via overlap-add as in DPRNN [1].

Parameters:	chunk_size (int) – Size of segmenting window. hop_size (int) – segmentation hop size.

References: [1] Yi Luo, Zhuo Chen and Takuya Yoshioka. “Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation” https://arxiv.org/abs/1910.06379

unfold(x)[source]¶

Unfold the feature tensor from $(batch, channels, time)$ to $(batch, channels, chunksize, nchunks)$.

Parameters:	x (`torch.Tensor`) – feature tensor of shape $(batch, channels, time)$.
Returns:	`torch.Tensor` – spliced feature tensor of shape $(batch, channels, chunksize, nchunks)$.

fold(x, output_size=None)[source]¶

Folds back the spliced feature tensor. Input shape $(batch, channels, chunksize, nchunks)$ to original shape $(batch, channels, time)$ using overlap-add.

Parameters:	x (`torch.Tensor`) – spliced feature tensor of shape $(batch, channels, chunksize, nchunks)$. output_size (int, optional) – sequence length of original feature tensor. If None, the original length cached by the previous call of `unfold()` will be used.
Returns:	`torch.Tensor` – feature tensor of shape $(batch, channels, time)$.

Note

fold caches the original length of the input.

static intra_process(x, module)[source]¶

Performs intra-chunk processing.

Parameters:	x (`torch.Tensor`) – spliced feature tensor of shape (batch, channels, chunk_size, n_chunks). module (`torch.nn.Module`) – module one wish to apply to each chunk of the spliced feature tensor.
Returns:	`torch.Tensor` – processed spliced feature tensor of shape $(batch, channels, chunksize, nchunks)$.

Note

the module should have the channel first convention and accept a 3D tensor of shape $(batch, channels, time)$.

static inter_process(x, module)[source]¶

Performs inter-chunk processing.

Parameters:	x (`torch.Tensor`) – spliced feature tensor of shape $(batch, channels, chunksize, nchunks)$. module (`torch.nn.Module`) – module one wish to apply between each chunk of the spliced feature tensor.
Returns:	x (`torch.Tensor`) – processed spliced feature tensor of shape $(batch, channels, chunksize, nchunks)$.

Note

the module should have the channel first convention and accept a 3D tensor of shape $(batch, channels, time)$.

Mixture Consistency¶

asteroid.dsp.mixture_consistency(mixture: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f769a1a10>, est_sources: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f6f3abf10>, src_weights: Optional[<sphinx.ext.autodoc.importer._MockObject object at 0x7f7f77b640d0>] = None, dim: int = 1) → <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f77b64490>[source]¶

Applies mixture consistency to a tensor of estimated sources.

Parameters:

mixture (torch.Tensor) – Mixture waveform or TF representation.
est_sources (torch.Tensor) – Estimated sources waveforms or TF representations.
src_weights (torch.Tensor) – Consistency weight for each source. Shape needs to be broadcastable to est_source. We make sure that the weights sum up to 1 along dim dim. If src_weights is None, compute them based on relative power.
dim (int) – Axis which contains the sources in est_sources.

Returns

torch.Tensor with same shape as est_sources, after applying mixture consistency.

Examples

>>> # Works on waveforms
>>> mix = torch.randn(10, 16000)
>>> est_sources = torch.randn(10, 2, 16000)
>>> new_est_sources = mixture_consistency(mix, est_sources, dim=1)
>>> # Also works on spectrograms
>>> mix = torch.randn(10, 514, 400)
>>> est_sources = torch.randn(10, 2, 514, 400)
>>> new_est_sources = mixture_consistency(mix, est_sources, dim=1)

Note

This method can be used only in ‘complete’ separation tasks, otherwise the residual error will contain unwanted sources. For example, this won’t work with the task “sep_noisy” from WHAM.

References: Scott Wisdom et al. “Differentiable consistency constraints for improved deep speech enhancement”, ICASSP 2019.

VAD¶

asteroid.dsp.vad.ebased_vad(mag_spec, th_db: int = 40)[source]¶

Compute energy-based VAD from a magnitude spectrogram (or equivalent).

Parameters:	mag_spec (torch.Tensor) – the spectrogram to perform VAD on. Expected shape (batch, , freq, time). The VAD mask will be computed independently for all the leading dimensions until the last two. Independent of the ordering of the last two dimensions. th_db* (int) – The threshold in dB from which a TF-bin is considered silent.
Returns:	`torch.BoolTensor`, the VAD mask.

Examples

>>> import torch
>>> mag_spec = torch.abs(torch.randn(10, 2, 65, 16))
>>> batch_src_mask = ebased_vad(mag_spec)

Delta Features¶

asteroid.dsp.deltas.compute_delta(feats: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f4c4bb110>, dim: int = -1) → <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f4c4bbad0>[source]¶

Compute delta coefficients of a tensor.

Parameters:	feats – Input features to compute deltas with. dim – feature dimension in the feats tensor.
Returns:	Tensor – Tensor of deltas.

Examples

>>> import torch
>>> phase = torch.randn(2, 257, 100)
>>> # Compute instantaneous frequency
>>> inst_freq = compute_delta(phase, dim=-1)
>>> # Or group delay
>>> group_delay = compute_delta(phase, dim=-2)

asteroid.dsp.deltas.concat_deltas(feats: <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f4c4bb050>, order: int = 1, dim: int = -1) → <sphinx.ext.autodoc.importer._MockObject object at 0x7f7f4c4bba10>[source]¶

Concatenate delta coefficients of a tensor to itself.

Parameters:	feats – Input features to compute deltas with. order – Order of the delta e.g with order==2, compute delta of delta as well. dim – feature dimension in the feats tensor.
Returns:	Tensor – Concatenation of the features, the deltas and subsequent deltas.

Examples

>>> import torch
>>> phase = torch.randn(2, 257, 100)
>>> # Compute second order instantaneous frequency
>>> phase_and_inst_freq = concat_deltas(phase, order=2, dim=-1)
>>> # Or group delay
>>> phase_and_group_delay = concat_deltas(phase, order=2, dim=-2)