Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition.
Jaeyoung KimMostafa El-KhamyJungwon LeePublished in: CoRR (2017)
Keyphrases
- speech recognition
- hidden markov models
- speech signal
- language model
- speech processing
- speech understanding
- neural network
- pattern recognition
- speaker identification
- speech synthesis
- speech recognition systems
- recurrent neural networks
- speech recognition technology
- information retrieval
- speaker dependent
- audio visual speech recognition