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