scene_renderer_cec1

Scene rendering for CEC1 challenge.

class clarity.data.scene_renderer_cec1.Renderer(input_path, output_path, num_channels=1, sample_rate=44100, ramp_duration=0.5, tail_duration=0.2, pre_duration=2.0, post_duration=1.0, test_nbits=16)[source]

Bases: object

SceneGenerator of CEC1 training and development sets. The render() function generates all simulated signals for each scene given the parameters specified in the metadata/scenes.train.json or metadata/scenes.dev.json file.

apply_brir(signal, brir)[source]

Convolve a signal with a binaural room impulse response (BRIR).

Parameters:

  • signal (ndarray) – The mono or stereo signal stored as array of floats

  • brir (ndarray) – The BRIR stored a 2xN array of floats

  • n_tail (int) – Truncate output to input signal length + n_tail

Returns:

The convolved signals

Return type:

ndarray

apply_ramp(signal, ramp_duration)[source]

Apply half cosine ramp into and out of signal.

Parameters:

  • signal (np.ndarray) – signal to be ramped.

  • ramp_duration (int) – ramp duration in seconds.

Returns:

Signal ramped into and out of by cosine function.

Return type:

np.ndarray

compute_snr(target: ndarray, noise: ndarray, pre_samples=0, post_samples=-1)[source]

Return the Signal Noise Ratio (SNR).

Take the overlapping segment of the noise and get the speech-weighted better ear Signal Noise Ratio. (Note, SNR is a ratio – not in dB.)

Parameters:

  • target (np.ndarray) – Target signal.

  • noise (np.ndarray) – Noise (should be same length as target)

Returns:

signal_noise_ratio for better ear.

Return type:

float

render(target_id: str, noise_type: str, interferer_id: str, room: str, scene: str, offset, snr_dB: int, dataset, pre_samples=88200, post_samples=44100)[source]
clarity.data.scene_renderer_cec1.check_scene_exists(scene: dict, output_path: str, num_channels: int) → bool[source]

Checks correct dataset directory for full set of pre-existing files.

Parameters:

  • scene (dict) – dictionary defining the scene to be generated.

  • output_path (str) – Path files should be saved to.

  • num_channels (int) – Number of channels

Returns:

boolean value indicating whether scene signals exist

or do not exist.

Return type:

status