This is a demo page for our accepted paper at Interspeech 2025, titled “DnR-nonverbal: Cinematic Audio Source Separation Dataset Containing Non-Verbal Sounds.”
Track Samples in Training Set of DnR-nonverbal
| Track ID | Mix | Speech (Reading + Non-Verbal) | Music | Effect |
|---|---|---|---|---|
| 100033 | ||||
| 104648 | ||||
| 139220 | ||||
| 155319 | ||||
| 191448 |
Separation Examples in Evaluation Set of DnR-nonverbal
Laughter
| Track ID | Mix | Target | Model Trained by DnR-v2 (Conventional) |
Model Trained by DnR-v2 + DnR-nonverbal (Proposed) |
|---|---|---|---|---|
| 105535 | ||||
| 179775 |
Whispering
| Track ID | Mix | Target | Model Trained by DnR-v2 (Conventional) |
Model Trained by DnR-v2 + DnR-nonverbal (Proposed) |
|---|---|---|---|---|
| 159585 | ||||
| 192289 |
Crying_and_sobbing
| Track ID | Mix | Target | Model Trained by DnR-v2 (Conventional) |
Model Trained by DnR-v2 + DnR-nonverbal (Proposed) |
|---|---|---|---|---|
| 131452 | ||||
| 145080 |
Screaming
| Track ID | Mix | Target | Model Trained by DnR-v2 (Conventional) |
Model Trained by DnR-v2 + DnR-nonverbal (Proposed) |
|---|---|---|---|---|
| 108347 | ||||
| 140083 |
Sigh
| Track ID | Mix | Target | Model Trained by DnR-v2 (Conventional) |
Model Trained by DnR-v2 + DnR-nonverbal (Proposed) |
|---|---|---|---|---|
| 179733 | ||||
| 185001 |
Shout
| Track ID | Mix | Target | Model Trained by DnR-v2 (Conventional) |
Model Trained by DnR-v2 + DnR-nonverbal (Proposed) |
|---|---|---|---|---|
| 124478 | ||||
| 180282 |