For example, if I have 3 audio classes including
- Ambulance Siren
- Police Car Siren
- Firetruck Siren
assuming these 3 classes could be distinguished by humans. If I just want the model to classify all these sounds as "Siren" sound only. What approach gives the better performance if I:
- Group these classes together into 1 class (Siren sound). and merge all datasets together.
- Separate these classes into their own individual categories.