Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition.
Gakuto KurataKartik AudhkhasiPublished in: SLT (2018)
Keyphrases
- end to end
- speech recognition
- bi directional
- hidden markov models
- language model
- speech synthesis
- automatic speech recognition
- speech processing
- speech signal
- congestion control
- speech recognition systems
- speech recognizer
- speaker identification
- pattern recognition
- speech recognition technology
- multimedia
- speaker independent
- associative memory
- n gram
- computer vision
- audio visual speech recognition