: Speech-Scene Graph Grounding Network for Speech-guided Navigation.
Dohyun KimYeseung KimJaehwi JangMinjae SongWoojin ChoiDaehyung ParkPublished in: RO-MAN (2023)
Keyphrases
- speech recognition
- speech synthesis
- text to speech
- spoken language
- speech signal
- network model
- dynamic networks
- automatic speech recognition
- audio visual
- network traffic
- input image
- object detection
- dialogue system
- spanning tree
- single image
- directed acyclic graph
- neural network
- dynamic scenes
- multiple objects
- multiple images
- graphical representation
- graph structure
- small world
- noisy environments
- complex networks
- three dimensional
- social networks