Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 2편

Planar Room Impulse Response Dataset - ACT, DTU Electro (b. 355 r. 008)

RIR dataset
RIR dataset 설명 보기

Dataset of Room Impulse Responses measured at the Acoustic Technology group facilities, DTU Electro. The measurements were carried out in building 355, room 008, otherwise known as the "sound field control" room. The dataset consists of measurements of the acoustic impulse response in a regular square grid of 80x80 cm2. The measurements consist of 30x30 room impulse responses (e.g. 900 RIRs) where the microphone, a 1/2 inch free field condenser measurement microphone (Br"uel&Kj"aer, N\ae rum, Denmark) was automatically positioned using a UR5 (Universal Robots, Odense, Denmark) scanning robotic arm. A BM6 loudspeaker (Dynaudio, Skanderborg, Denmark) placed in a room corner was used to excite the room with 5s wideband logarithmic sweeps. The data are available as H5 (Hierarchical Data Formats) with the following structure: Dataset "Sound field control room - HDF5 datastructure" Dataset.attributes ├── calibration (1) '94.33 dB @ 1.14 kHz' ├── fs (1) 48000 Hz ├── grid_bottom (3x900) [[2.76, 2.32, 2.73, ... 2.738 2.76..., ...]] m ├── loudspeaker_position (3) [5.779 0.263 0.904] m ├── room_dimensions (3) [6.124 5.771 3.073] m ├── sweep_amplitude (1) 0.4 ├── sweep_duration (1) 5 s ├── sweep_range (2) [32. 12000.] Hz ├── temperature (1) 20.3 °C └── true_calibration (1) '94.19 dB @ 1.17 kHz' Dataset.groups ├── Noise_recs_bottom (12x3x144000) float64 ├── RIRs_bottom (900x25439) float64 (e.g. 900 positions) └── sweep_signal (288000) float64 Use with Matlab: https://mathworks.com/help/matlab/hdf5-files.html Use with Python: https://docs.h5py.org/en/stable/

관련 논문 1편

CUBE B-format Ambisonic RIR dataset

CUBE B-format Ambisonic RIR dataset 설명 보기

This dataset includes 720 directional B-format RIRs, i.e. first-order Ambisonic room impulse responses, measured at 30 receiver positions with 1m spacing in an equidistant grid (4xm) with 24 hemispherical source positions each. The measurements were carried out at the IEM CUBE using Soundfield ST450 MKII microphones. The data is saved according to the SOFA convention (https://www.sofaconventions.org/mediawiki/index.php). The SOFA Matlab/Octave API is available at https://github.com/sofacoustics/API_MO.5. Unfortunately, the used SOFA convention (MultiPerspectiveAmbisonicRIR) was never integrated into the official SOFA conventions. However, it can be found at: https://github.com/jdemuynke/API_MO/tree/master/API_MO/conventions. The dataset can be found here: https://phaidra.kug.ac.at/view/o:104435. Contact: kaspar.mueller@cerence.com; zotter@iem.at