Investigating the Impact of Spectral and Temporal Degradation on End-to-End Automatic Speech Recognition Performance.
Takanori AshiharaTakafumi MoriyaMakio KashinoPublished in: Interspeech (2021)
Keyphrases
- end to end
- automatic speech recognition
- speech recognition
- speech signal
- conversational speech
- word error rate
- broadcast news
- speaker adaptation
- hidden markov models
- speech retrieval
- wireless ad hoc networks
- admission control
- spoken words
- speech sounds
- noisy environments
- congestion control
- spontaneous speech
- recognition errors
- scalable video
- transport layer
- neural network
- linear prediction
- internet protocol
- super resolution
- feature extraction
- machine learning