MultiRoomTransitionDataset

The Multi Room Transition Dataset contains 4,032 measured room impulse responses from three complex indoor environments. For each environment, four stationary loudspeakers were measured with both a binaural KEMAR and a four-channel Zoom H3-VR receiver. irdl downloads only the SOFA file selected by environment, receiver, and loudspeaker.

The provider files use the SingleRoomSRIR SOFA convention and include measurement positions. They were recorded at 48 kHz and are available under a Creative Commons Attribution 4.0 license.

Dataset details and visual documentation are available in the MRTD Zenodo record.

class irdl.MultiRoomTransitionDataset

Bases: BaseDataset

Download the MRTD dataset from Zenodo.

_category = 'room_impulse_responses'

_download(provider_dir: Path, **dataset_kwargs) → Path

Download the requested native SOFA file from Zenodo.

_environments = frozenset({'hallways-lecturehall', 'offices', 'workshops'})

_receivers = frozenset({'kemar', 'zoom'})

_source_filename(**dataset_kwargs) → str

Return the provider’s SOFA filename for the requested setup.

_validate_params(**dataset_kwargs) → None

Validate the MRTD environment, receiver, and loudspeaker.

doi: str = '10.5281/zenodo.13341566'

classmethod get(environment: str = 'offices', receiver: str = 'kemar', loudspeaker: int = 1, cache_dir: Path | str | None = None, export_dir: Path | str | None = None, output_format: str = 'pyfar') → dict | Path | None

Download the MRTD dataset from Zenodo.

DOI: https://doi.org/10.5281/zenodo.13341566

Parameters:

cache_dirstr

Cache directory for downloads. Defaults is the OS user cache directory. This default can be overridden by setting IRDL_CACHE_DIR environment variable.

export_dirstr, optional

Directory for final output. If specified, the data will be exported to <export_dir/MRTD/>. Else, it remains in <cache_dir/output/>.

output_formatstr

Output format: ‘pyfar’, ‘numpy’, ‘hdf5’, ‘sofa’, or ‘raw’.

environmentstr, optional

Acoustic environment. One of ‘hallways-lecturehall’, ‘offices’, or ‘workshops’. Default is ‘offices’.

receiverstr, optional

‘kemar’ selects the binaural KEMAR and ‘zoom’ selects the four-channel Zoom H3-VR. Default is ‘kemar’.

loudspeakerint, optional

Stationary loudspeaker number from 1 through 4. Default is 1.

Returns:

dict or Path

For ‘pyfar’ / ‘numpy’: dict of in-memory objects. For ‘sofa’ / ‘hdf5’ / ‘raw’: Path to file on disk.

name: str = 'mrtd'