This page includes audio samples for CoNMod: Controllable Neural Frame-based Modulation Effects

Link for the paper

Input dry audio

input_dry_10s.wav

Studio One Phaser

Audio output for seen LFO frequency and feedback

LFO frequency 0.23Hz

feedback 0%

output

inference_out_LFO_fq=0.23_ctrl=0.0.wav

target

inference_target_LFO_fq=0.23_ctrl=0.0.wav

feedback 25%

output

inference_out_LFO_fq=0.23_ctrl=0.25.wav

target

inference_target_LFO_fq=0.23_ctrl=0.25.wav

feedback 50%

output

inference_out_LFO_fq=0.23_ctrl=0.5.wav

target

inference_target_LFO_fq=0.23_ctrl=0.5.wav

feedback 75%

output

inference_out_LFO_fq=0.23_ctrl=0.75.wav

target

inference_target_LFO_fq=0.23_ctrl=0.75.wav

LFO frequency 0.73Hz

feedback 0%

output

inference_out_LFO_fq=0.73_ctrl=0.0.wav

target

inference_target_LFO_fq=0.73_ctrl=0.0.wav

feedback 25%

output

inference_out_LFO_fq=0.73_ctrl=0.25.wav

target

inference_target_LFO_fq=0.73_ctrl=0.25.wav

feedback 50%

output

inference_out_LFO_fq=0.73_ctrl=0.5.wav

target

inference_target_LFO_fq=0.73_ctrl=0.5.wav

feedback 75%

output

inference_out_LFO_fq=0.73_ctrl=0.75.wav

target

inference_target_LFO_fq=0.73_ctrl=0.75.wav

LFO frequency 1.13Hz

feedback 0%

output

inference_out_LFO_fq=1.13_ctrl=0.0.wav

target

inference_target_LFO_fq=1.13_ctrl=0.0.wav

feedback 25%

output

inference_out_LFO_fq=1.13_ctrl=0.25.wav

target

inference_target_LFO_fq=1.13_ctrl=0.25.wav

feedback 50%

output

inference_out_LFO_fq=1.13_ctrl=0.5.wav

target

inference_target_LFO_fq=1.13_ctrl=0.5.wav

feedback 75%

output

inference_out_LFO_fq=1.13_ctrl=0.75.wav

target

inference_target_LFO_fq=1.13_ctrl=0.75.wav

Audio output for unseen LFO frequency and feedback

Studio One Flanger

Audio output for seen LFO frequency and feedback

Audio output for unseen LFO frequency and feedback

Mooer phaser

Audio output for seen LFO frequency and feedback

Audio output for unseen LFO frequency and feedback