End-to-End Speech-to-Dialog-Act Recognition.
Viet-Trung DangTianyu ZhaoSei UenoHirofumi InagumaTatsuya KawaharaPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- recognition engine
- congestion control
- wireless ad hoc networks
- admission control
- speech recognition
- multipath
- feature extraction
- text localization and recognition
- spoken dialog systems
- ad hoc networks
- rate allocation
- rate adaptation
- spoken dialog
- content delivery
- application layer
- automatic speech recognition
- high bandwidth
- signal to noise ratio
- real world
- internet protocol
- low complexity