End-to-End Speech Intelligibility Prediction Using Time-Domain Fully Convolutional Neural Networks.
Mathias Bach PedersenMorten KolbækAsger Heidemann AndersenSøren Holdt JensenJesper JensenPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- convolutional neural networks
- speech recognition
- convolutional network
- admission control
- congestion control
- ad hoc networks
- prediction error
- multipath
- wireless ad hoc networks
- frequency domain
- scalable video
- high bandwidth
- internet protocol
- text localization and recognition
- computational complexity
- application layer
- content delivery