SquimObjective

class torchaudio.models.SquimObjective(encoder: Module, dprnn: Module, branches: ModuleList)

Speech Quality and Intelligibility Measures (SQUIM) model that predicts objective metric scores for speech enhancement (e.g., STOI, PESQ, and SI-SDR).

Parameters:

• encoder (torch.nn.Module) – Encoder module to transform 1D waveform to 2D feature representation.

• dprnn (torch.nn.Module) – DPRNN module to model sequential feature.

• branches (torch.nn.ModuleList) – Transformer branches in which each branch estimate one objective metirc score.

Tutorials using SquimObjective:

Torchaudio-Squim: Non-intrusive Speech Assessment in TorchAudio

Torchaudio-Squim: Non-intrusive Speech Assessment in TorchAudio

Methods

forward

SquimObjective.forward(x: Tensor) → List[Tensor]

Parameters:

x (torch.Tensor) – Input waveforms. Tensor with dimensions (batch, time).

Returns:

List of score Tenosrs. Each Tensor is with dimension (batch,).

Return type:

List(torch.Tensor)

Factory Functions

squim_objective_model	Build a custome torchaudio.prototype.models.SquimObjective model.
squim_objective_base	Build torchaudio.prototype.models.SquimObjective model with default arguments.