The dEchorate dataset

Diego Di Carlo, Pinchas Tandeitnik, Cédric Foy, Nancy Bertin, Antoine Deleforge, Sharon GannotZenodo 2021 · DOI · OpenAlex

Abstract

Please make sure you are checking the - last updated version of the HDF5 dataset - last update version of the SOFA dataset This work presents a new dataset of measured multichannel Room Impulse Responses (RIRs) named <em><strong>dEchorate</strong></em>.<br> See the `README.md` file on the code repository on visit the dEchorate website for more information: Paper | ArXiv | Website | Code | Data HDF5 and Python | Data SOFA It includes annotations of early echo timings and 3D positions of microphones, real sources and image sources under different wall configurations in a cuboid room. These data provide a tool for bench-marking recent methods in echo-aware signal processing, such as <em>speech enhancement</em>, <em>room geometry estimation</em>, <em>RIR estimation</em>, <em>acoustic echo retrieval</em>, <em>microphone calibration,</em> <em>echo labeling</em> and <em>reflectors position estimation</em>. The dataset is provided with software utilities to easily access, manipulate and visualize the data as well as baseline methods for echo-related tasks. If you use the data in your research, please reference the paper (not just the Zenodo record) <pre><code class="language-bash">@article{dicarlo2021dechorate, title={dEchorate: a calibrated room impulse response dataset for echo-aware signal processing}, author={{Di Carlo}, Diego and Tandeitnik, Pinchas and Foy, Cedri{\'c} and Bertin, Nancy and Deleforge, Antoine and Gannot, Sharon}, journal={EURASIP Journal on Audio, Speech, and Music Processing}, volume={2021}, number={1}, pages={1--15}, year={2021}, publisher={Springer} }</code></pre>
BibTeX
@inproceedings{carlo2021dechorate,
  author = {Diego Di Carlo and Pinchas Tandeitnik and Cédric Foy and Nancy Bertin and Antoine Deleforge and Sharon Gannot},
  title = {{The dEchorate dataset}},
  booktitle = {Zenodo},
  year = {2021},
  doi = {10.5281/zenodo.4626589},
}

Loading related content...

Figure