torch_msbg

An FIR-based torch implementation of approximated MSBG hearing loss model

class clarity.predictor.torch_msbg.MSBGHearingModel(audiogram: ndarray, audiometric: ndarray, sr: int = 44100, spl_cali: bool = True, src_position: str = 'ff', kernel_size: int = 1025, device: str | None = None)

Bases: Module

calibrate_spl(x: Tensor) → Tensor

f_smear

settings for recruitment

forward(x: Tensor) → Tensor

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

gt_fir_sin

settings for spl calibration

measure_rms(wav: Tensor) → Tensor

Compute RMS level of a signal.

Measures total power of all 10 msec frames that are above a specified

threshold of db_relative_rms

Parameters:

wav – input signal

Returns:

RMS level in dB

recruitment(x: Tensor) → Tensor

recruitment_fir(x: Tensor) → Tensor

recruitment_out_coef

settings for FIR Gammatone Filters

smear(x: Tensor) → Tensor

Padding issue needs to be worked out

src_to_cochlea_filt(x: Tensor, cochlea_filter: Tensor) → Tensor

training: bool

class clarity.predictor.torch_msbg.torchloudnorm(sample_rate: int = 44100, norm_lufs: int = -36, kernel_size: int = 1025, block_size: float = 0.4, overlap: float = 0.75, gamma_a: int = -70, device: str | None = None)

Bases: Module

apply_filter(x: Tensor) → Tensor

forward(x: Tensor) → Tensor

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

high_pass

rms measurement

integrated_loudness(x: Tensor) → Tensor

normalize_loudness(x: Tensor, lufs: Tensor) → Tensor

training: bool