o yi @szddlZddlZddlmZddlmZddlmZer#ddlm Z ndZ dgZ dded ed e d e d e d ef ddZdS)N)Tensor)_check_same_shape)_PYSTOI_AVAILABLE)stoi$short_time_objective_intelligibilityFpredstargetfsextendedkeep_same_devicereturnc Cststdt||t|jdkr+t||||}t |}nU| d|jd}| d|jd}t j |jdd}t|jdD]} t|| ddf|| ddf|||| <qYt |}| |jdd}|r||j}|S)agCalculates STOI (Short-Time Objective Intelligibility) metric for evaluating speech signals. Intelligibility measure which is highly correlated with the intelligibility of degraded speech signals, e.g., due to additive noise, single-/multi-channel noise reduction, binary masking and vocoded speech as in CI simulations. The STOI- measure is intrusive, i.e., a function of the clean and degraded speech signals. STOI may be a good alternative to the speech intelligibility index (SII) or the speech transmission index (STI), when you are interested in the effect of nonlinear processing to noisy speech, e.g., noise reduction, binary masking algorithms, on speech intelligibility. Description taken from `Cees Taal's website`_ and for further defails see `STOI ref1`_ and `STOI ref2`_. This metric is a wrapper for the `pystoi package`_. As the implementation backend implementation only supports calculations on CPU, all input will automatically be moved to CPU to perform the metric calculation before being moved back to the original device. .. note:: using this metrics requires you to have ``pystoi`` install. Either install as ``pip install torchmetrics[audio]`` or ``pip install pystoi`` Args: preds: float tensor with shape ``(...,time)`` target: float tensor with shape ``(...,time)`` fs: sampling frequency (Hz) extended: whether to use the extended STOI described in `STOI ref3`_. keep_same_device: whether to move the stoi value to the device of preds Returns: stoi value of shape [...] Raises: ModuleNotFoundError: If ``pystoi`` package is not installed RuntimeError: If ``preds`` and ``target`` does not have the same shape Example: >>> from torchmetrics.functional.audio.stoi import short_time_objective_intelligibility >>> import torch >>> g = torch.manual_seed(1) >>> preds = torch.randn(8000) >>> target = torch.randn(8000) >>> short_time_objective_intelligibility(preds, target, 8000).float() tensor(-0.0100) zShortTimeObjectiveIntelligibility metric requires that `pystoi` is installed. Either install as `pip install torchmetrics[audio]` or `pip install pystoi`.r)shapeN)rModuleNotFoundErrorrlenr stoi_backenddetachcpunumpytorchtensorreshapenpemptyrange from_numpytodevice) rrr r r stoi_val_npstoi_valpreds_np target_npbr$V/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/audio/stoi.pyrs$, & ,  )FF)rrrrtorchmetrics.utilities.checksrtorchmetrics.utilities.importsrpystoirr__doctest_skip__intboolrr$r$r$r%s.