Sound event synthesis using WaveNet
This is a demonstration of sound event synthesis (SES) using event labels based on the conditional WaveNet [1]. As the dataset, we used 10 different sound events (manual coffee grinder, cup clinking, alarm clock ringing, whistle, maracas, drum, electric shaver, trash box banging, tearing paper, bell ringing) contained in the RWCP-SSD (Real World Computing Partnership-Sound Scene Database) [2].
You can download a zip file of original and synthesized sounds from here.
・Manual coffee grinder
coffee_grinder_original.wavOriginal sound
coffee_grinder_generated.wavSynthesized sound
・Cup
cup_original.wavOriginal sound
cup_generated.wavSynthesized sound
・Clock
clock_original.wavOriginal sound
clock_generated.wavSynthesized sound
・Whistle
whistle_original.wavOriginal sound
whistle_generated.wavSynthesized sound
・Maracas
maracas_original.wavOriginal sound
maracas_genarated.wavSynthesized sound
・Drum
drum_original.wavOriginal sound
drum_generated.wavSynthesized sound
・Shaver
shaver_original.wavOriginal sound
shaver_generated.wavSynthesized sound
・Trash box
trashbox_original.wavOriginal sound
trashbox_generated.wavSynthesized sound
・Tearing paper
tearing_original.wavOriginal sound
tearing_generated.wavSynthesized sound
・Bell
bell_original.wavOriginal sound
bell_generated.wavSynthesized sound
[1] A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, “WaveNet: A Generative Model for Raw Audio,” arXiv preprint, arXiv:1609.03499, 2016.[2] S. Nakamura, K. Hiyane, F. Asano, and T. Endo, “Acoustical Sound Database in Real Environments for Sound Scene Understanding and Hands-free Speech Recognition,” Proc. LanguageResources and Evaluation Conference (LREC), pp. 965–968, 2000.