Complex Scale-Invariant Signal-to-Noise Ratio (C-SI-SNR)

Module Interface

class torchmetrics.audio.ComplexScaleInvariantSignalNoiseRatio(zero_mean=False, **kwargs)

Calculate Complex scale-invariant signal-to-noise ratio (C-SI-SNR) metric for evaluating quality of audio.

As input to forward and update the metric accepts the following input

• preds (Tensor): real float tensor with shape (...,frequency,time,2) or complex float tensor with shape (..., frequency,time)

• target (Tensor): real float tensor with shape (...,frequency,time,2) or complex float tensor with shape (..., frequency,time)

As output of forward and compute the metric returns the following output

• c_si_snr (Tensor): float scalar tensor with average C-SI-SNR value over samples

Parameters:

• zero_mean (bool) – if to zero mean target and preds or not

• kwargs (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Raises:

• ValueError – If zero_mean is not an bool

• TypeError – If preds is not the shape (…, frequency, time, 2) (after being converted to real if it is complex). If preds and target does not have the same shape.

Example

>>> from torch import randn
>>> from torchmetrics.audio import ComplexScaleInvariantSignalNoiseRatio
>>> preds = randn((1,257,100,2))
>>> target = randn((1,257,100,2))
>>> c_si_snr = ComplexScaleInvariantSignalNoiseRatio()
>>> c_si_snr(preds, target)
tensor(-38.8832)

plot(val=None, ax=None)

Plot a single or multiple values from the metric.

Parameters:

• val (Union[Tensor, Sequence[Tensor], None]) – Either a single result from calling metric.forward or metric.compute or a list of these results. If no value is provided, will automatically call metric.compute and plot that result.

• ax (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value
>>> import torch
>>> from torchmetrics.audio import ComplexScaleInvariantSignalNoiseRatio
>>> metric = ComplexScaleInvariantSignalNoiseRatio()
>>> metric.update(torch.rand(1,257,100,2), torch.rand(1,257,100,2))
>>> fig_, ax_ = metric.plot()

>>> # Example plotting multiple values
>>> import torch
>>> from torchmetrics.audio import ComplexScaleInvariantSignalNoiseRatio
>>> metric = ComplexScaleInvariantSignalNoiseRatio()
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(torch.rand(1,257,100,2), torch.rand(1,257,100,2)))
>>> fig_, ax_ = metric.plot(values)

Functional Interface

torchmetrics.functional.audio.complex_scale_invariant_signal_noise_ratio(preds, target, zero_mean=False)

Complex scale-invariant signal-to-noise ratio (C-SI-SNR).

Parameters:

• preds (Tensor) – real float tensor with shape (...,frequency,time,2) or complex float tensor with shape (..., frequency,time)

• target (Tensor) – real float tensor with shape (...,frequency,time,2) or complex float tensor with shape (..., frequency,time)

• zero_mean (bool) – When set to True, the mean of all signals is subtracted prior to computation of the metrics

Return type:

Tensor

Returns:

Float tensor with shape (...,) of C-SI-SNR values per sample

Raises:

RuntimeError – If preds is not the shape (…,frequency,time,2) (after being converted to real if it is complex). If preds and target does not have the same shape.

Example

>>> from torch import randn
>>> from torchmetrics.functional.audio import complex_scale_invariant_signal_noise_ratio
>>> preds = randn((1,257,100,2))
>>> target = randn((1,257,100,2))
>>> complex_scale_invariant_signal_noise_ratio(preds, target)
tensor([-38.8832])