Exploring Neural Transducers for End-to-End Speech Recognition.
Eric BattenbergJitong ChenRewon ChildAdam CoatesYashesh GaurYi LiHairong LiuSanjeev SatheeshDavid SeetapunAnuroop SriramZhenyao ZhuPublished in: CoRR (2017)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- network architecture
- automatic speech recognition
- speech processing
- speech synthesis
- speech signal
- neural network
- speech recognition systems
- pattern recognition
- speech recognition technology
- noisy environments
- speech recognizers
- congestion control
- speech recognizer
- speaker identification
- speaker independent
- real world
- acoustic models