SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Model

Return index page

Enviromental Sound Morphing (ESC50)

This page contains demonstration of environmental sound morphing.

This section we demonstrate how SoundMorpher smoothly morph source environmental sound to the target environmental sound cross different categories. Source and target audio recordings are randomly selected from ESC50 dataset. The ESC50 dataset are sourced from ESC50-git.



1. Dog and cat vocial morphing

Example 1

Source audio

Target audio




α=0.0




α=1.0

Example 2

Source audio

Target audio




α=0.0




α=1.0

Example 3

Source audio

Target audio




α=0.0




α=1.0


2. Baby crying and laughing human sounds morphing

Example 1

Source audio

Target audio




α=0.0




α=1.0

Example 2

Source audio

Target audio




α=0.0




α=1.0

Example 3

Source audio

Target audio




α=0.0




α=1.0


3. Church bells and clock alarm sounds morphing

Example 1

Source audio

Target audio




α=0.0




α=1.0

Example 2

Source audio

Target audio




α=0.0




α=1.0

Example 3

Source audio

Target audio




α=0.0




α=1.0


4. Wood door knocking and clapping sounds morphing

Example 1

Source audio

Target audio




α=0.0




α=1.0

Example 2

Source audio

Target audio




α=0.0




α=1.0

Example 3

Source audio

Target audio




α=0.0




α=1.0


Return index page