Reducing bandwidth for robust distributed speech recognition in conditions of packet loss.
Ronan FlynnEdward JonesPublished in: Speech Commun. (2012)
Keyphrases
- speech recognition
- packet loss
- packet losses
- transmission rate
- noisy environments
- streaming video
- bandwidth requirements
- network congestion
- congestion control
- hidden markov models
- error propagation
- video quality
- packet loss rate
- error concealment
- language model
- automatic speech recognition
- pattern recognition
- speech signal
- speech recognizer
- video transmission
- error resilience
- multiple description coding
- speaker identification
- end to end
- speech recognition systems
- rate adaptation
- video coding
- image processing
- wireless channels
- background noise
- video streaming
- peer to peer
- computational complexity