├── .gitignore ├── CommandLines.md ├── LICENSE ├── README.md ├── Setup-commands.txt ├── compose_gar_key_visual.png ├── composing-gar-table3.png ├── to_evar ├── config │ ├── ast_fusion.yaml │ ├── cnn14_fusion.yaml │ ├── vggish_fusion.yaml │ └── vggish_fusion919.yaml └── evar │ ├── ar_ast_ext.py │ ├── ar_cnn14_ext.py │ └── ar_vggish_ext.py ├── to_gp_cnn14.patch ├── to_gp_vggish.patch └── tutorial ├── 563746_cat.wav ├── Tutorial1-Encoding-Audio-BYOL-A.ipynb ├── Tutorial2-Visualize-Audios-BYOL-A.ipynb ├── Tutorial3-Try-VGGish-Variants.ipynb ├── Tutorial4-Try-CNN14-Variants.ipynb ├── Tutorial5-Visualize-Dataset-Samples.ipynb ├── barking-shibainu.wav ├── cat-haru.jpg └── shibainu-toro.jpg /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/.gitignore -------------------------------------------------------------------------------- /CommandLines.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/CommandLines.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/README.md -------------------------------------------------------------------------------- /Setup-commands.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/Setup-commands.txt -------------------------------------------------------------------------------- /compose_gar_key_visual.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/compose_gar_key_visual.png -------------------------------------------------------------------------------- /composing-gar-table3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/composing-gar-table3.png -------------------------------------------------------------------------------- /to_evar/config/ast_fusion.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/config/ast_fusion.yaml -------------------------------------------------------------------------------- /to_evar/config/cnn14_fusion.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/config/cnn14_fusion.yaml -------------------------------------------------------------------------------- /to_evar/config/vggish_fusion.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/config/vggish_fusion.yaml -------------------------------------------------------------------------------- /to_evar/config/vggish_fusion919.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/config/vggish_fusion919.yaml -------------------------------------------------------------------------------- /to_evar/evar/ar_ast_ext.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/evar/ar_ast_ext.py -------------------------------------------------------------------------------- /to_evar/evar/ar_cnn14_ext.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/evar/ar_cnn14_ext.py -------------------------------------------------------------------------------- /to_evar/evar/ar_vggish_ext.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_evar/evar/ar_vggish_ext.py -------------------------------------------------------------------------------- /to_gp_cnn14.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_gp_cnn14.patch -------------------------------------------------------------------------------- /to_gp_vggish.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/to_gp_vggish.patch -------------------------------------------------------------------------------- /tutorial/563746_cat.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/563746_cat.wav -------------------------------------------------------------------------------- /tutorial/Tutorial1-Encoding-Audio-BYOL-A.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/Tutorial1-Encoding-Audio-BYOL-A.ipynb -------------------------------------------------------------------------------- /tutorial/Tutorial2-Visualize-Audios-BYOL-A.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/Tutorial2-Visualize-Audios-BYOL-A.ipynb -------------------------------------------------------------------------------- /tutorial/Tutorial3-Try-VGGish-Variants.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/Tutorial3-Try-VGGish-Variants.ipynb -------------------------------------------------------------------------------- /tutorial/Tutorial4-Try-CNN14-Variants.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/Tutorial4-Try-CNN14-Variants.ipynb -------------------------------------------------------------------------------- /tutorial/Tutorial5-Visualize-Dataset-Samples.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/Tutorial5-Visualize-Dataset-Samples.ipynb -------------------------------------------------------------------------------- /tutorial/barking-shibainu.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/barking-shibainu.wav -------------------------------------------------------------------------------- /tutorial/cat-haru.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/cat-haru.jpg -------------------------------------------------------------------------------- /tutorial/shibainu-toro.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nttcslab/composing-general-audio-repr/HEAD/tutorial/shibainu-toro.jpg --------------------------------------------------------------------------------