End-to-End Neural Segmental Models for Speech Recognition.
Hao TangLiang LuLingpeng KongKevin GimpelKaren LivescuChris DyerNoah A. SmithSteve RenalsPublished in: IEEE J. Sel. Top. Signal Process. (2017)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- acoustic models
- speech recognizer
- language model
- pattern recognition
- speech synthesis
- automatic speech recognition
- noisy environments
- probabilistic model
- speech signal
- speech recognition systems
- congestion control
- speaker independent
- neural network
- audio visual speech recognition
- maximum likelihood
- face recognition
- image processing