Deep context: end-to-end contextual speech recognition.
Golan PundakTara N. SainathRohit PrabhavalkarAnjuli KannanDing ZhaoPublished in: CoRR (2018)
Keyphrases
- end to end
- speech recognition
- contextual information
- hidden markov models
- speech processing
- pattern recognition
- speech signal
- speech recognizer
- language model
- speech recognition technology
- automatic speech recognition
- speech synthesis
- noisy environments
- speech retrieval
- speaker dependent
- speech recognition systems
- speaker identification
- congestion control
- neural network
- audio visual speech recognition
- machine learning
- acoustic models
- noise reduction
- isolated word