Trainable Dynamic Subsampling for End-to-End Speech Recognition.
Shucong ZhangErfan LoweimiYumo XuPeter BellSteve RenalsPublished in: INTERSPEECH (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- automatic speech recognition
- pattern recognition
- noisy environments
- speech synthesis
- speech processing
- speech signal
- speech recognition technology
- language model
- speaker identification
- congestion control
- speech retrieval
- speech recognizer
- speech recognition systems
- speaker independent
- machine learning
- isolated word
- speaker diarization
- packet loss
- speaker adaptation
- speaker dependent
- signal to noise ratio
- probabilistic model
- speech recognizers
- neural network
- audio visual speech recognition