Published June 28, 2023 | Version v1
Video/Audio Open

DCASE 2023 Challenge Task 7 Submission

  • 1. Gaudio Lab, inc.
  • 2. Gaudio Lab, inc. / KAIST
  • 3. Carnegie Mellon University
  • 4. New York University
  • 5. Doshisha University
  • 6. Ritsumeikan University
  • 7. CNRS, Ecole Centrale Nantes, Nantes Université
  • 8. The University of Tokyo

Description

Description

These audio files are the generated sound samples from the submission systems for the DCASE 2023 Challenge Task 7 "Foley Sound Synthesis". The audio data of each submission consists of 700 sound excerpts, which are divided into 7 classes. Each sound excerpt is a mono 16-bit 22,050 Hz 4-second audio. The classes of audio are as follows.

  • DogBark
  • Footstep
  • GunShot
  • Keyboard
  • MovingMotorVehicle
  • Rain
  • Sneeze/Cough

Directory structure

- /Submissions
    - /A
        - /TASys02
            - /dog_bark
                - /00.wav
                - /....wav
                - /99.wav
            - /footstep
            - /gunshot
            - /keyboard
            - /moving_motor_vehicle
            - /rain
            - /sneeze_cough
        - ...  
        - /TASys11  
    - /B
        - /TBSys01
        - ...  
        - /TBSys31  

Contact

  • Keunwoo Choi, keunwoo@gaudiolab.com
  • Jaekwon Im, jakeoneijk@kaist.ac.kr

Files

dcase_task7_submission_meta.csv

Files (3.3 GB)

Name Size Download all
md5:f457129db523f20f8edeb2f14707b083
3.3 GB Download
md5:4ca7cc963e20b4b983315393ce1600c8
1.4 kB Preview Download