Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework.
Johanes EffendiAndros TjandraSakriani SaktiSatoshi NakamuraPublished in: CoRR (2020)
Keyphrases
- image data
- image analysis
- three dimensional
- ground truth
- image database
- input image
- object recognition
- image features
- multiple images
- multi modal
- probabilistic model
- image retrieval
- image classification
- computer graphics
- segmentation method
- image matching
- rigid body
- image collections
- region of interest
- test images
- image quality
- edge detection
- image registration