Segmental Recurrent Neural Networks for End-to-End Speech Recognition.
Liang LuLingpeng KongChris DyerNoah A. SmithSteve RenalsPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- end to end
- recurrent neural networks
- hidden markov models
- neural network
- feed forward
- speech synthesis
- language model
- speech processing
- echo state networks
- speech recognizer
- speaker identification
- recurrent networks
- congestion control
- speech signal
- speech recognition technology
- automatic speech recognition
- noisy environments
- artificial neural networks
- pattern recognition
- speaker dependent
- multi stream
- speech recognition systems
- speaker independent