Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification.
Paul PrimusHamid Eghbal-zadehDavid EitelsebnerKhaled KoutiniAndreas ArztGerhard WidmerPublished in: DCASE (2019)
Keyphrases
- scene classification
- audio recordings
- bird species
- object recognition
- natural scenes
- indoor outdoor
- image classification
- biologically inspired
- visual words
- image representation
- scene recognition
- bag of features
- music information retrieval
- multiscale
- natural images
- higher order
- bag of words
- search engine
- pairwise
- image sequences