Perceptual Evaluation of Speech Quality (PESQ)¶
Module Interface¶
- class torchmetrics.audio.pesq.PerceptualEvaluationSpeechQuality(fs, mode, n_processes=1, **kwargs)[source]
Calculates Perceptual Evaluation of Speech Quality (PESQ). It’s a recognized industry standard for audio quality that takes into considerations characteristics such as: audio sharpness, call volume, background noise, clipping, audio interference ect. PESQ returns a score between -0.5 and 4.5 with the higher scores indicating a better quality.
This metric is a wrapper for the pesq package. Note that input will be moved to
cpu
to perform the metric calculation.As input to
forward
andupdate
the metric accepts the following inputpreds
(Tensor
): float tensor with shape(...,time)
target
(Tensor
): float tensor with shape(...,time)
As output of forward and compute the metric returns the following output
pesq
(Tensor
): float tensor with shape(...,)
of PESQ value per sample
Note
using this metrics requires you to have
pesq
install. Either install aspip install torchmetrics[audio]
orpip install pesq
.pesq
will compile with your currently installed version of numpy, meaning that if you upgrade numpy at some point in the future you will most likely have to reinstallpesq
.- Parameters
fs¶ (
int
) – sampling frequency, should be 16000 or 8000 (Hz)keep_same_device¶ – whether to move the pesq value to the device of preds
n_processes¶ (
int
) – integer specifiying the number of processes to run in parallel for the metric calculation. Only applies to batches of data and ifmultiprocessing
package is installed.kwargs¶ (
Any
) – Additional keyword arguments, see Advanced metric settings for more info.
- Raises
ModuleNotFoundError – If
pesq
package is not installedValueError – If
fs
is not either8000
or16000
ValueError – If
mode
is not either"wb"
or"nb"
Example
>>> from torchmetrics.audio.pesq import PerceptualEvaluationSpeechQuality >>> import torch >>> g = torch.manual_seed(1) >>> preds = torch.randn(8000) >>> target = torch.randn(8000) >>> nb_pesq = PerceptualEvaluationSpeechQuality(8000, 'nb') >>> nb_pesq(preds, target) tensor(2.2076) >>> wb_pesq = PerceptualEvaluationSpeechQuality(16000, 'wb') >>> wb_pesq(preds, target) tensor(1.7359)
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Functional Interface¶
- torchmetrics.functional.audio.pesq.perceptual_evaluation_speech_quality(preds, target, fs, mode, keep_same_device=False, n_processes=1)[source]
Calculates Perceptual Evaluation of Speech Quality (PESQ). It’s a recognized industry standard for audio quality that takes into considerations characteristics such as: audio sharpness, call volume, background noise, clipping, audio interference ect. PESQ returns a score between -0.5 and 4.5 with the higher scores indicating a better quality.
This metric is a wrapper for the pesq package. Note that input will be moved to cpu to perform the metric calculation.
Note
using this metrics requires you to have
pesq
install. Either install aspip install torchmetrics[audio]
orpip install pesq
. Note thatpesq
will compile with your currently installed version of numpy, meaning that if you upgrade numpy at some point in the future you will most likely have to reinstallpesq
.- Parameters
fs¶ (
int
) – sampling frequency, should be 16000 or 8000 (Hz)keep_same_device¶ (
bool
) – whether to move the pesq value to the device of predsn_processes¶ (
int
) – integer specifiying the number of processes to run in parallel for the metric calculation. Only applies to batches of data and ifmultiprocessing
package is installed.
- Return type
- Returns
Float tensor with shape
(...,)
of PESQ values per sample- Raises
ModuleNotFoundError – If
pesq
package is not installedValueError – If
fs
is not either8000
or16000
ValueError – If
mode
is not either"wb"
or"nb"
RuntimeError – If
preds
andtarget
do not have the same shape
Example
>>> from torchmetrics.functional.audio.pesq import perceptual_evaluation_speech_quality >>> import torch >>> g = torch.manual_seed(1) >>> preds = torch.randn(8000) >>> target = torch.randn(8000) >>> perceptual_evaluation_speech_quality(preds, target, 8000, 'nb') tensor(2.2076) >>> perceptual_evaluation_speech_quality(preds, target, 16000, 'wb') tensor(1.7359)